diff --git "a/checkpoint-2747520/trainer_state.json" "b/checkpoint-2747520/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2747520/trainer_state.json" @@ -0,0 +1,32509 @@ +{ + "best_metric": 3.8400161266326904, + "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/npi-only/transformer/1/checkpoints/checkpoint-1068480", + "epoch": 0.025000606015738065, + "eval_steps": 10, + "global_step": 2747520, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 4.999998362119627e-05, + "loss": 10.9232, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.999161405248948e-05, + "loss": 6.8136, + "step": 512 + }, + { + "epoch": 0.0, + "learning_rate": 4.998322810497896e-05, + "loss": 6.1808, + "step": 1024 + }, + { + "epoch": 0.0, + "learning_rate": 4.997484215746844e-05, + "loss": 5.976, + "step": 1536 + }, + { + "epoch": 0.0, + "learning_rate": 4.996645620995792e-05, + "loss": 5.8215, + "step": 2048 + }, + { + "epoch": 0.0, + "learning_rate": 4.99580702624474e-05, + "loss": 5.713, + "step": 2560 + }, + { + "epoch": 0.0, + "learning_rate": 4.994968431493688e-05, + "loss": 5.61, + "step": 3072 + }, + { + "epoch": 0.0, + "learning_rate": 4.994129836742636e-05, + "loss": 5.5443, + "step": 3584 + }, + { + "epoch": 0.0, + "learning_rate": 4.993291241991584e-05, + "loss": 5.4534, + "step": 4096 + }, + { + "epoch": 0.0, + "learning_rate": 4.992452647240532e-05, + "loss": 5.4147, + "step": 4608 + }, + { + "epoch": 0.0, + "learning_rate": 4.99161405248948e-05, + "loss": 5.3633, + "step": 5120 + }, + { + "epoch": 0.0, + "learning_rate": 4.990775457738428e-05, + "loss": 5.3228, + "step": 5632 + }, + { + "epoch": 0.0, + "learning_rate": 4.989938500867749e-05, + "loss": 5.2592, + "step": 6144 + }, + { + "epoch": 0.0, + "learning_rate": 4.989099906116697e-05, + "loss": 5.2219, + "step": 6656 + }, + { + "epoch": 0.0, + "learning_rate": 4.988261311365645e-05, + "loss": 5.1884, + "step": 7168 + }, + { + "epoch": 0.0, + "learning_rate": 4.987422716614593e-05, + "loss": 5.1394, + "step": 7680 + }, + { + "epoch": 0.0, + "learning_rate": 4.986584121863541e-05, + "loss": 5.1226, + "step": 8192 + }, + { + "epoch": 0.0, + "learning_rate": 4.985745527112489e-05, + "loss": 5.089, + "step": 8704 + }, + { + "epoch": 0.0, + "learning_rate": 4.984906932361437e-05, + "loss": 5.0496, + "step": 9216 + }, + { + "epoch": 0.0, + "learning_rate": 4.984068337610385e-05, + "loss": 5.0283, + "step": 9728 + }, + { + "epoch": 0.0, + "learning_rate": 4.983229742859333e-05, + "loss": 5.0114, + "step": 10240 + }, + { + "epoch": 0.0, + "learning_rate": 4.9823927859886547e-05, + "loss": 4.981, + "step": 10752 + }, + { + "epoch": 0.0, + "learning_rate": 4.9815541912376026e-05, + "loss": 4.9633, + "step": 11264 + }, + { + "epoch": 0.0, + "learning_rate": 4.9807155964865506e-05, + "loss": 4.9298, + "step": 11776 + }, + { + "epoch": 0.0, + "learning_rate": 4.9798770017354986e-05, + "loss": 4.9221, + "step": 12288 + }, + { + "epoch": 0.0, + "learning_rate": 4.9790400448648195e-05, + "loss": 4.9022, + "step": 12800 + }, + { + "epoch": 0.0, + "learning_rate": 4.9782014501137675e-05, + "loss": 4.8784, + "step": 13312 + }, + { + "epoch": 0.0, + "learning_rate": 4.9773628553627155e-05, + "loss": 4.857, + "step": 13824 + }, + { + "epoch": 0.0, + "learning_rate": 4.9765242606116635e-05, + "loss": 4.8314, + "step": 14336 + }, + { + "epoch": 0.0, + "learning_rate": 4.9756873037409844e-05, + "loss": 4.824, + "step": 14848 + }, + { + "epoch": 0.01, + "learning_rate": 4.9748487089899324e-05, + "loss": 4.8069, + "step": 15360 + }, + { + "epoch": 0.01, + "learning_rate": 4.9740101142388804e-05, + "loss": 4.8009, + "step": 15872 + }, + { + "epoch": 0.01, + "learning_rate": 4.9731715194878284e-05, + "loss": 4.7843, + "step": 16384 + }, + { + "epoch": 0.01, + "learning_rate": 4.97233456261715e-05, + "loss": 4.7694, + "step": 16896 + }, + { + "epoch": 0.01, + "learning_rate": 4.971495967866098e-05, + "loss": 4.7615, + "step": 17408 + }, + { + "epoch": 0.01, + "learning_rate": 4.970657373115046e-05, + "loss": 4.7503, + "step": 17920 + }, + { + "epoch": 0.01, + "learning_rate": 4.969818778363994e-05, + "loss": 4.739, + "step": 18432 + }, + { + "epoch": 0.01, + "learning_rate": 4.968980183612942e-05, + "loss": 4.7088, + "step": 18944 + }, + { + "epoch": 0.01, + "learning_rate": 4.96814158886189e-05, + "loss": 4.707, + "step": 19456 + }, + { + "epoch": 0.01, + "learning_rate": 4.967302994110837e-05, + "loss": 4.6818, + "step": 19968 + }, + { + "epoch": 0.01, + "learning_rate": 4.966464399359785e-05, + "loss": 4.6879, + "step": 20480 + }, + { + "epoch": 0.01, + "learning_rate": 4.965627442489107e-05, + "loss": 4.6677, + "step": 20992 + }, + { + "epoch": 0.01, + "learning_rate": 4.964788847738054e-05, + "loss": 4.6699, + "step": 21504 + }, + { + "epoch": 0.01, + "learning_rate": 4.963950252987002e-05, + "loss": 4.649, + "step": 22016 + }, + { + "epoch": 0.01, + "learning_rate": 4.96311165823595e-05, + "loss": 4.6457, + "step": 22528 + }, + { + "epoch": 0.01, + "learning_rate": 4.962274701365272e-05, + "loss": 4.6376, + "step": 23040 + }, + { + "epoch": 0.01, + "learning_rate": 4.96143610661422e-05, + "loss": 4.6291, + "step": 23552 + }, + { + "epoch": 0.01, + "learning_rate": 4.960597511863168e-05, + "loss": 4.6187, + "step": 24064 + }, + { + "epoch": 0.01, + "learning_rate": 4.959758917112116e-05, + "loss": 4.5937, + "step": 24576 + }, + { + "epoch": 0.01, + "learning_rate": 4.9589219602414374e-05, + "loss": 4.6004, + "step": 25088 + }, + { + "epoch": 0.01, + "learning_rate": 4.958083365490385e-05, + "loss": 4.601, + "step": 25600 + }, + { + "epoch": 0.01, + "learning_rate": 4.957244770739333e-05, + "loss": 4.5946, + "step": 26112 + }, + { + "epoch": 0.01, + "learning_rate": 4.956406175988281e-05, + "loss": 4.5739, + "step": 26624 + }, + { + "epoch": 0.01, + "learning_rate": 4.9555692191176016e-05, + "loss": 4.5624, + "step": 27136 + }, + { + "epoch": 0.01, + "learning_rate": 4.954732262246923e-05, + "loss": 4.5642, + "step": 27648 + }, + { + "epoch": 0.01, + "learning_rate": 4.953893667495871e-05, + "loss": 4.55, + "step": 28160 + }, + { + "epoch": 0.01, + "learning_rate": 4.953055072744819e-05, + "loss": 4.5649, + "step": 28672 + }, + { + "epoch": 0.01, + "learning_rate": 4.952216477993767e-05, + "loss": 4.5261, + "step": 29184 + }, + { + "epoch": 0.01, + "learning_rate": 4.951377883242715e-05, + "loss": 4.5434, + "step": 29696 + }, + { + "epoch": 0.01, + "learning_rate": 4.950539288491663e-05, + "loss": 4.5326, + "step": 30208 + }, + { + "epoch": 0.01, + "learning_rate": 4.949700693740611e-05, + "loss": 4.5126, + "step": 30720 + }, + { + "epoch": 0.01, + "learning_rate": 4.948862098989559e-05, + "loss": 4.5224, + "step": 31232 + }, + { + "epoch": 0.01, + "learning_rate": 4.94802514211888e-05, + "loss": 4.5079, + "step": 31744 + }, + { + "epoch": 0.01, + "learning_rate": 4.947186547367828e-05, + "loss": 4.4979, + "step": 32256 + }, + { + "epoch": 0.01, + "learning_rate": 4.946347952616776e-05, + "loss": 4.4943, + "step": 32768 + }, + { + "epoch": 0.01, + "learning_rate": 4.945509357865724e-05, + "loss": 4.5034, + "step": 33280 + }, + { + "epoch": 0.01, + "learning_rate": 4.944672400995045e-05, + "loss": 4.4827, + "step": 33792 + }, + { + "epoch": 0.01, + "learning_rate": 4.943833806243993e-05, + "loss": 4.4789, + "step": 34304 + }, + { + "epoch": 0.01, + "learning_rate": 4.942995211492941e-05, + "loss": 4.471, + "step": 34816 + }, + { + "epoch": 0.01, + "learning_rate": 4.942156616741889e-05, + "loss": 4.4655, + "step": 35328 + }, + { + "epoch": 0.01, + "learning_rate": 4.9413196598712105e-05, + "loss": 4.4722, + "step": 35840 + }, + { + "epoch": 0.01, + "learning_rate": 4.940482703000532e-05, + "loss": 4.477, + "step": 36352 + }, + { + "epoch": 0.01, + "learning_rate": 4.9396441082494794e-05, + "loss": 4.4526, + "step": 36864 + }, + { + "epoch": 0.01, + "learning_rate": 4.9388055134984274e-05, + "loss": 4.4636, + "step": 37376 + }, + { + "epoch": 0.01, + "learning_rate": 4.9379669187473754e-05, + "loss": 4.4666, + "step": 37888 + }, + { + "epoch": 0.01, + "learning_rate": 4.9371283239963234e-05, + "loss": 4.4495, + "step": 38400 + }, + { + "epoch": 0.01, + "learning_rate": 4.936291367125644e-05, + "loss": 4.4365, + "step": 38912 + }, + { + "epoch": 0.01, + "learning_rate": 4.935452772374592e-05, + "loss": 4.4387, + "step": 39424 + }, + { + "epoch": 0.01, + "learning_rate": 4.93461417762354e-05, + "loss": 4.4364, + "step": 39936 + }, + { + "epoch": 0.01, + "learning_rate": 4.933775582872488e-05, + "loss": 4.4224, + "step": 40448 + }, + { + "epoch": 0.01, + "learning_rate": 4.932936988121436e-05, + "loss": 4.4195, + "step": 40960 + }, + { + "epoch": 0.01, + "learning_rate": 4.932098393370384e-05, + "loss": 4.4287, + "step": 41472 + }, + { + "epoch": 0.01, + "learning_rate": 4.931259798619332e-05, + "loss": 4.4282, + "step": 41984 + }, + { + "epoch": 0.01, + "learning_rate": 4.930421203868281e-05, + "loss": 4.4123, + "step": 42496 + }, + { + "epoch": 0.01, + "learning_rate": 4.929584246997602e-05, + "loss": 4.3904, + "step": 43008 + }, + { + "epoch": 0.01, + "learning_rate": 4.92874565224655e-05, + "loss": 4.4031, + "step": 43520 + }, + { + "epoch": 0.01, + "learning_rate": 4.927907057495498e-05, + "loss": 4.4074, + "step": 44032 + }, + { + "epoch": 0.01, + "learning_rate": 4.927068462744446e-05, + "loss": 4.3974, + "step": 44544 + }, + { + "epoch": 0.01, + "learning_rate": 4.926231505873767e-05, + "loss": 4.3991, + "step": 45056 + }, + { + "epoch": 0.01, + "learning_rate": 4.925394549003088e-05, + "loss": 4.3821, + "step": 45568 + }, + { + "epoch": 0.02, + "learning_rate": 4.924555954252036e-05, + "loss": 4.3804, + "step": 46080 + }, + { + "epoch": 0.02, + "learning_rate": 4.923717359500984e-05, + "loss": 4.3754, + "step": 46592 + }, + { + "epoch": 0.02, + "learning_rate": 4.922878764749932e-05, + "loss": 4.3731, + "step": 47104 + }, + { + "epoch": 0.02, + "learning_rate": 4.92204016999888e-05, + "loss": 4.3787, + "step": 47616 + }, + { + "epoch": 0.02, + "learning_rate": 4.921201575247828e-05, + "loss": 4.3669, + "step": 48128 + }, + { + "epoch": 0.02, + "learning_rate": 4.920364618377149e-05, + "loss": 4.3841, + "step": 48640 + }, + { + "epoch": 0.02, + "learning_rate": 4.919526023626097e-05, + "loss": 4.3662, + "step": 49152 + }, + { + "epoch": 0.02, + "learning_rate": 4.918687428875045e-05, + "loss": 4.3504, + "step": 49664 + }, + { + "epoch": 0.02, + "learning_rate": 4.917848834123993e-05, + "loss": 4.352, + "step": 50176 + }, + { + "epoch": 0.02, + "learning_rate": 4.917010239372941e-05, + "loss": 4.3593, + "step": 50688 + }, + { + "epoch": 0.02, + "learning_rate": 4.916171644621889e-05, + "loss": 4.351, + "step": 51200 + }, + { + "epoch": 0.02, + "learning_rate": 4.915333049870837e-05, + "loss": 4.3494, + "step": 51712 + }, + { + "epoch": 0.02, + "learning_rate": 4.914494455119785e-05, + "loss": 4.3473, + "step": 52224 + }, + { + "epoch": 0.02, + "learning_rate": 4.913657498249106e-05, + "loss": 4.337, + "step": 52736 + }, + { + "epoch": 0.02, + "learning_rate": 4.912818903498054e-05, + "loss": 4.3398, + "step": 53248 + }, + { + "epoch": 0.02, + "learning_rate": 4.911980308747002e-05, + "loss": 4.3189, + "step": 53760 + }, + { + "epoch": 0.02, + "learning_rate": 4.91114171399595e-05, + "loss": 4.3246, + "step": 54272 + }, + { + "epoch": 0.02, + "learning_rate": 4.910304757125272e-05, + "loss": 4.3298, + "step": 54784 + }, + { + "epoch": 0.02, + "learning_rate": 4.90946616237422e-05, + "loss": 4.3238, + "step": 55296 + }, + { + "epoch": 0.02, + "learning_rate": 4.908627567623168e-05, + "loss": 4.3181, + "step": 55808 + }, + { + "epoch": 0.02, + "learning_rate": 4.907788972872115e-05, + "loss": 4.3261, + "step": 56320 + }, + { + "epoch": 0.02, + "learning_rate": 4.906950378121063e-05, + "loss": 4.3007, + "step": 56832 + }, + { + "epoch": 0.02, + "learning_rate": 4.906111783370011e-05, + "loss": 4.3122, + "step": 57344 + }, + { + "epoch": 0.02, + "learning_rate": 4.9052748264993326e-05, + "loss": 4.3079, + "step": 57856 + }, + { + "epoch": 0.02, + "learning_rate": 4.90443623174828e-05, + "loss": 4.3116, + "step": 58368 + }, + { + "epoch": 0.02, + "learning_rate": 4.903597636997228e-05, + "loss": 4.3183, + "step": 58880 + }, + { + "epoch": 0.02, + "learning_rate": 4.902759042246176e-05, + "loss": 4.3073, + "step": 59392 + }, + { + "epoch": 0.02, + "learning_rate": 4.9019237232558704e-05, + "loss": 4.2984, + "step": 59904 + }, + { + "epoch": 0.02, + "learning_rate": 4.9010851285048184e-05, + "loss": 4.2929, + "step": 60416 + }, + { + "epoch": 0.02, + "learning_rate": 4.900246533753767e-05, + "loss": 4.3001, + "step": 60928 + }, + { + "epoch": 0.02, + "learning_rate": 4.899407939002715e-05, + "loss": 4.2944, + "step": 61440 + }, + { + "epoch": 0.02, + "learning_rate": 4.8985693442516624e-05, + "loss": 4.2926, + "step": 61952 + }, + { + "epoch": 0.02, + "learning_rate": 4.8977307495006104e-05, + "loss": 4.2851, + "step": 62464 + }, + { + "epoch": 0.02, + "learning_rate": 4.8968921547495584e-05, + "loss": 4.2819, + "step": 62976 + }, + { + "epoch": 0.02, + "learning_rate": 4.8960535599985064e-05, + "loss": 4.2825, + "step": 63488 + }, + { + "epoch": 0.02, + "learning_rate": 4.8952149652474544e-05, + "loss": 4.2709, + "step": 64000 + }, + { + "epoch": 0.02, + "learning_rate": 4.8943763704964024e-05, + "loss": 4.2795, + "step": 64512 + }, + { + "epoch": 0.02, + "learning_rate": 4.8935377757453504e-05, + "loss": 4.2758, + "step": 65024 + }, + { + "epoch": 0.02, + "learning_rate": 4.892700818874671e-05, + "loss": 4.2697, + "step": 65536 + }, + { + "epoch": 0.02, + "learning_rate": 4.891862224123619e-05, + "loss": 4.2613, + "step": 66048 + }, + { + "epoch": 0.02, + "learning_rate": 4.891023629372567e-05, + "loss": 4.2795, + "step": 66560 + }, + { + "epoch": 0.02, + "learning_rate": 4.890185034621515e-05, + "loss": 4.2796, + "step": 67072 + }, + { + "epoch": 0.02, + "learning_rate": 4.889346439870464e-05, + "loss": 4.2674, + "step": 67584 + }, + { + "epoch": 0.02, + "learning_rate": 4.888507845119412e-05, + "loss": 4.2552, + "step": 68096 + }, + { + "epoch": 0.02, + "learning_rate": 4.887670888248733e-05, + "loss": 4.2636, + "step": 68608 + }, + { + "epoch": 0.02, + "learning_rate": 4.886832293497681e-05, + "loss": 4.2639, + "step": 69120 + }, + { + "epoch": 0.02, + "learning_rate": 4.885993698746629e-05, + "loss": 4.2627, + "step": 69632 + }, + { + "epoch": 0.02, + "learning_rate": 4.885155103995577e-05, + "loss": 4.2588, + "step": 70144 + }, + { + "epoch": 0.02, + "learning_rate": 4.884318147124898e-05, + "loss": 4.2586, + "step": 70656 + }, + { + "epoch": 0.02, + "learning_rate": 4.883479552373846e-05, + "loss": 4.2527, + "step": 71168 + }, + { + "epoch": 0.02, + "learning_rate": 4.882640957622794e-05, + "loss": 4.2502, + "step": 71680 + }, + { + "epoch": 0.02, + "learning_rate": 4.881802362871742e-05, + "loss": 4.2447, + "step": 72192 + }, + { + "epoch": 0.02, + "learning_rate": 4.88096376812069e-05, + "loss": 4.2488, + "step": 72704 + }, + { + "epoch": 0.02, + "learning_rate": 4.880125173369638e-05, + "loss": 4.2398, + "step": 73216 + }, + { + "epoch": 0.02, + "learning_rate": 4.8792882164989586e-05, + "loss": 4.2344, + "step": 73728 + }, + { + "epoch": 0.02, + "learning_rate": 4.878449621747907e-05, + "loss": 4.2476, + "step": 74240 + }, + { + "epoch": 0.02, + "learning_rate": 4.877611026996855e-05, + "loss": 4.2317, + "step": 74752 + }, + { + "epoch": 0.02, + "learning_rate": 4.876772432245803e-05, + "loss": 4.2424, + "step": 75264 + }, + { + "epoch": 0.02, + "learning_rate": 4.875933837494751e-05, + "loss": 4.2295, + "step": 75776 + }, + { + "epoch": 0.02, + "learning_rate": 4.875096880624072e-05, + "loss": 4.224, + "step": 76288 + }, + { + "epoch": 0.03, + "eval_loss": 4.19596529006958, + "eval_runtime": 307.6211, + "eval_samples_per_second": 1240.458, + "eval_steps_per_second": 38.765, + "step": 76320 + }, + { + "epoch": 1.0, + "learning_rate": 4.87425828587302e-05, + "loss": 4.2161, + "step": 76800 + }, + { + "epoch": 1.0, + "learning_rate": 4.873419691121968e-05, + "loss": 4.2145, + "step": 77312 + }, + { + "epoch": 1.0, + "learning_rate": 4.872581096370916e-05, + "loss": 4.2271, + "step": 77824 + }, + { + "epoch": 1.0, + "learning_rate": 4.8717425016198635e-05, + "loss": 4.2185, + "step": 78336 + }, + { + "epoch": 1.0, + "learning_rate": 4.8709039068688115e-05, + "loss": 4.2223, + "step": 78848 + }, + { + "epoch": 1.0, + "learning_rate": 4.870066949998133e-05, + "loss": 4.2098, + "step": 79360 + }, + { + "epoch": 1.0, + "learning_rate": 4.869228355247081e-05, + "loss": 4.2089, + "step": 79872 + }, + { + "epoch": 1.0, + "learning_rate": 4.868389760496029e-05, + "loss": 4.1976, + "step": 80384 + }, + { + "epoch": 1.0, + "learning_rate": 4.867551165744977e-05, + "loss": 4.2139, + "step": 80896 + }, + { + "epoch": 1.0, + "learning_rate": 4.866712570993925e-05, + "loss": 4.2054, + "step": 81408 + }, + { + "epoch": 1.0, + "learning_rate": 4.865875614123246e-05, + "loss": 4.2174, + "step": 81920 + }, + { + "epoch": 1.0, + "learning_rate": 4.865037019372194e-05, + "loss": 4.199, + "step": 82432 + }, + { + "epoch": 1.0, + "learning_rate": 4.8642000625015155e-05, + "loss": 4.1959, + "step": 82944 + }, + { + "epoch": 1.0, + "learning_rate": 4.8633614677504635e-05, + "loss": 4.1895, + "step": 83456 + }, + { + "epoch": 1.0, + "learning_rate": 4.862522872999411e-05, + "loss": 4.1857, + "step": 83968 + }, + { + "epoch": 1.0, + "learning_rate": 4.861684278248359e-05, + "loss": 4.1848, + "step": 84480 + }, + { + "epoch": 1.0, + "learning_rate": 4.860845683497307e-05, + "loss": 4.1926, + "step": 84992 + }, + { + "epoch": 1.0, + "learning_rate": 4.860007088746255e-05, + "loss": 4.181, + "step": 85504 + }, + { + "epoch": 1.0, + "learning_rate": 4.859168493995203e-05, + "loss": 4.1791, + "step": 86016 + }, + { + "epoch": 1.0, + "learning_rate": 4.858329899244151e-05, + "loss": 4.1997, + "step": 86528 + }, + { + "epoch": 1.0, + "learning_rate": 4.8574929423734724e-05, + "loss": 4.1842, + "step": 87040 + }, + { + "epoch": 1.0, + "learning_rate": 4.8566543476224204e-05, + "loss": 4.1846, + "step": 87552 + }, + { + "epoch": 1.0, + "learning_rate": 4.8558157528713684e-05, + "loss": 4.1733, + "step": 88064 + }, + { + "epoch": 1.0, + "learning_rate": 4.8549771581203164e-05, + "loss": 4.186, + "step": 88576 + }, + { + "epoch": 1.0, + "learning_rate": 4.854140201249637e-05, + "loss": 4.1715, + "step": 89088 + }, + { + "epoch": 1.0, + "learning_rate": 4.853301606498585e-05, + "loss": 4.1731, + "step": 89600 + }, + { + "epoch": 1.0, + "learning_rate": 4.852463011747533e-05, + "loss": 4.1706, + "step": 90112 + }, + { + "epoch": 1.0, + "learning_rate": 4.851624416996481e-05, + "loss": 4.1629, + "step": 90624 + }, + { + "epoch": 1.0, + "learning_rate": 4.850787460125802e-05, + "loss": 4.159, + "step": 91136 + }, + { + "epoch": 1.01, + "learning_rate": 4.84994886537475e-05, + "loss": 4.158, + "step": 91648 + }, + { + "epoch": 1.01, + "learning_rate": 4.849110270623698e-05, + "loss": 4.1673, + "step": 92160 + }, + { + "epoch": 1.01, + "learning_rate": 4.848271675872646e-05, + "loss": 4.1656, + "step": 92672 + }, + { + "epoch": 1.01, + "learning_rate": 4.847434719001968e-05, + "loss": 4.1599, + "step": 93184 + }, + { + "epoch": 1.01, + "learning_rate": 4.846596124250916e-05, + "loss": 4.1656, + "step": 93696 + }, + { + "epoch": 1.01, + "learning_rate": 4.845757529499864e-05, + "loss": 4.1609, + "step": 94208 + }, + { + "epoch": 1.01, + "learning_rate": 4.844918934748812e-05, + "loss": 4.1605, + "step": 94720 + }, + { + "epoch": 1.01, + "learning_rate": 4.844081977878133e-05, + "loss": 4.1478, + "step": 95232 + }, + { + "epoch": 1.01, + "learning_rate": 4.843243383127081e-05, + "loss": 4.1481, + "step": 95744 + }, + { + "epoch": 1.01, + "learning_rate": 4.842404788376029e-05, + "loss": 4.1373, + "step": 96256 + }, + { + "epoch": 1.01, + "learning_rate": 4.841566193624977e-05, + "loss": 4.15, + "step": 96768 + }, + { + "epoch": 1.01, + "learning_rate": 4.840727598873925e-05, + "loss": 4.1347, + "step": 97280 + }, + { + "epoch": 1.01, + "learning_rate": 4.8398906420032456e-05, + "loss": 4.1489, + "step": 97792 + }, + { + "epoch": 1.01, + "learning_rate": 4.8390520472521936e-05, + "loss": 4.1351, + "step": 98304 + }, + { + "epoch": 1.01, + "learning_rate": 4.8382134525011416e-05, + "loss": 4.1394, + "step": 98816 + }, + { + "epoch": 1.01, + "learning_rate": 4.83737485775009e-05, + "loss": 4.1396, + "step": 99328 + }, + { + "epoch": 1.01, + "learning_rate": 4.836537900879411e-05, + "loss": 4.1371, + "step": 99840 + }, + { + "epoch": 1.01, + "learning_rate": 4.835699306128359e-05, + "loss": 4.1348, + "step": 100352 + }, + { + "epoch": 1.01, + "learning_rate": 4.834860711377307e-05, + "loss": 4.1203, + "step": 100864 + }, + { + "epoch": 1.01, + "learning_rate": 4.834022116626255e-05, + "loss": 4.1246, + "step": 101376 + }, + { + "epoch": 1.01, + "learning_rate": 4.833185159755576e-05, + "loss": 4.1364, + "step": 101888 + }, + { + "epoch": 1.01, + "learning_rate": 4.832346565004524e-05, + "loss": 4.1332, + "step": 102400 + }, + { + "epoch": 1.01, + "learning_rate": 4.831507970253472e-05, + "loss": 4.1238, + "step": 102912 + }, + { + "epoch": 1.01, + "learning_rate": 4.83066937550242e-05, + "loss": 4.1138, + "step": 103424 + }, + { + "epoch": 1.01, + "learning_rate": 4.829832418631741e-05, + "loss": 4.1229, + "step": 103936 + }, + { + "epoch": 1.01, + "learning_rate": 4.828993823880689e-05, + "loss": 4.11, + "step": 104448 + }, + { + "epoch": 1.01, + "learning_rate": 4.828155229129637e-05, + "loss": 4.1329, + "step": 104960 + }, + { + "epoch": 1.01, + "learning_rate": 4.8273166343785856e-05, + "loss": 4.1041, + "step": 105472 + }, + { + "epoch": 1.01, + "learning_rate": 4.8264796775079065e-05, + "loss": 4.1261, + "step": 105984 + }, + { + "epoch": 1.01, + "learning_rate": 4.8256410827568545e-05, + "loss": 4.1179, + "step": 106496 + }, + { + "epoch": 1.01, + "learning_rate": 4.8248024880058025e-05, + "loss": 4.1028, + "step": 107008 + }, + { + "epoch": 1.01, + "learning_rate": 4.8239638932547505e-05, + "loss": 4.1151, + "step": 107520 + }, + { + "epoch": 1.01, + "learning_rate": 4.8231269363840714e-05, + "loss": 4.1112, + "step": 108032 + }, + { + "epoch": 1.01, + "learning_rate": 4.8222883416330194e-05, + "loss": 4.0991, + "step": 108544 + }, + { + "epoch": 1.01, + "learning_rate": 4.8214497468819674e-05, + "loss": 4.1038, + "step": 109056 + }, + { + "epoch": 1.01, + "learning_rate": 4.8206111521309154e-05, + "loss": 4.1144, + "step": 109568 + }, + { + "epoch": 1.01, + "learning_rate": 4.819774195260236e-05, + "loss": 4.1019, + "step": 110080 + }, + { + "epoch": 1.01, + "learning_rate": 4.818935600509184e-05, + "loss": 4.1004, + "step": 110592 + }, + { + "epoch": 1.01, + "learning_rate": 4.818097005758132e-05, + "loss": 4.0964, + "step": 111104 + }, + { + "epoch": 1.01, + "learning_rate": 4.817258411007081e-05, + "loss": 4.0942, + "step": 111616 + }, + { + "epoch": 1.01, + "learning_rate": 4.816421454136402e-05, + "loss": 4.1035, + "step": 112128 + }, + { + "epoch": 1.01, + "learning_rate": 4.81558285938535e-05, + "loss": 4.1158, + "step": 112640 + }, + { + "epoch": 1.01, + "learning_rate": 4.814744264634298e-05, + "loss": 4.0961, + "step": 113152 + }, + { + "epoch": 1.01, + "learning_rate": 4.813905669883246e-05, + "loss": 4.1094, + "step": 113664 + }, + { + "epoch": 1.01, + "learning_rate": 4.813068713012567e-05, + "loss": 4.1096, + "step": 114176 + }, + { + "epoch": 1.01, + "learning_rate": 4.812230118261515e-05, + "loss": 4.0974, + "step": 114688 + }, + { + "epoch": 1.01, + "learning_rate": 4.811391523510463e-05, + "loss": 4.089, + "step": 115200 + }, + { + "epoch": 1.01, + "learning_rate": 4.810552928759411e-05, + "loss": 4.0998, + "step": 115712 + }, + { + "epoch": 1.01, + "learning_rate": 4.809715971888732e-05, + "loss": 4.0974, + "step": 116224 + }, + { + "epoch": 1.01, + "learning_rate": 4.80887737713768e-05, + "loss": 4.088, + "step": 116736 + }, + { + "epoch": 1.01, + "learning_rate": 4.808038782386628e-05, + "loss": 4.0883, + "step": 117248 + }, + { + "epoch": 1.01, + "learning_rate": 4.807200187635576e-05, + "loss": 4.0946, + "step": 117760 + }, + { + "epoch": 1.01, + "learning_rate": 4.806363230764897e-05, + "loss": 4.1017, + "step": 118272 + }, + { + "epoch": 1.01, + "learning_rate": 4.805524636013845e-05, + "loss": 4.0884, + "step": 118784 + }, + { + "epoch": 1.01, + "learning_rate": 4.804686041262793e-05, + "loss": 4.0768, + "step": 119296 + }, + { + "epoch": 1.01, + "learning_rate": 4.803847446511741e-05, + "loss": 4.082, + "step": 119808 + }, + { + "epoch": 1.01, + "learning_rate": 4.803010489641062e-05, + "loss": 4.0887, + "step": 120320 + }, + { + "epoch": 1.01, + "learning_rate": 4.80217189489001e-05, + "loss": 4.0863, + "step": 120832 + }, + { + "epoch": 1.01, + "learning_rate": 4.801333300138958e-05, + "loss": 4.0892, + "step": 121344 + }, + { + "epoch": 1.01, + "learning_rate": 4.800496343268279e-05, + "loss": 4.0766, + "step": 121856 + }, + { + "epoch": 1.02, + "learning_rate": 4.799657748517227e-05, + "loss": 4.0722, + "step": 122368 + }, + { + "epoch": 1.02, + "learning_rate": 4.798819153766175e-05, + "loss": 4.0715, + "step": 122880 + }, + { + "epoch": 1.02, + "learning_rate": 4.797980559015123e-05, + "loss": 4.0741, + "step": 123392 + }, + { + "epoch": 1.02, + "learning_rate": 4.797141964264071e-05, + "loss": 4.0767, + "step": 123904 + }, + { + "epoch": 1.02, + "learning_rate": 4.796303369513019e-05, + "loss": 4.0739, + "step": 124416 + }, + { + "epoch": 1.02, + "learning_rate": 4.795464774761967e-05, + "loss": 4.094, + "step": 124928 + }, + { + "epoch": 1.02, + "learning_rate": 4.794626180010915e-05, + "loss": 4.0777, + "step": 125440 + }, + { + "epoch": 1.02, + "learning_rate": 4.793789223140236e-05, + "loss": 4.061, + "step": 125952 + }, + { + "epoch": 1.02, + "learning_rate": 4.792950628389184e-05, + "loss": 4.0699, + "step": 126464 + }, + { + "epoch": 1.02, + "learning_rate": 4.792112033638132e-05, + "loss": 4.0729, + "step": 126976 + }, + { + "epoch": 1.02, + "learning_rate": 4.79127343888708e-05, + "loss": 4.0726, + "step": 127488 + }, + { + "epoch": 1.02, + "learning_rate": 4.790436482016401e-05, + "loss": 4.0715, + "step": 128000 + }, + { + "epoch": 1.02, + "learning_rate": 4.789597887265349e-05, + "loss": 4.068, + "step": 128512 + }, + { + "epoch": 1.02, + "learning_rate": 4.788759292514297e-05, + "loss": 4.0614, + "step": 129024 + }, + { + "epoch": 1.02, + "learning_rate": 4.787920697763245e-05, + "loss": 4.0714, + "step": 129536 + }, + { + "epoch": 1.02, + "learning_rate": 4.7870837408925664e-05, + "loss": 4.0442, + "step": 130048 + }, + { + "epoch": 1.02, + "learning_rate": 4.7862451461415144e-05, + "loss": 4.0587, + "step": 130560 + }, + { + "epoch": 1.02, + "learning_rate": 4.785408189270836e-05, + "loss": 4.0595, + "step": 131072 + }, + { + "epoch": 1.02, + "learning_rate": 4.784569594519783e-05, + "loss": 4.0604, + "step": 131584 + }, + { + "epoch": 1.02, + "learning_rate": 4.783730999768731e-05, + "loss": 4.051, + "step": 132096 + }, + { + "epoch": 1.02, + "learning_rate": 4.782892405017679e-05, + "loss": 4.0618, + "step": 132608 + }, + { + "epoch": 1.02, + "learning_rate": 4.782053810266627e-05, + "loss": 4.0482, + "step": 133120 + }, + { + "epoch": 1.02, + "learning_rate": 4.781215215515575e-05, + "loss": 4.052, + "step": 133632 + }, + { + "epoch": 1.02, + "learning_rate": 4.780376620764523e-05, + "loss": 4.0537, + "step": 134144 + }, + { + "epoch": 1.02, + "learning_rate": 4.779539663893844e-05, + "loss": 4.054, + "step": 134656 + }, + { + "epoch": 1.02, + "learning_rate": 4.778701069142792e-05, + "loss": 4.0698, + "step": 135168 + }, + { + "epoch": 1.02, + "learning_rate": 4.77786247439174e-05, + "loss": 4.0596, + "step": 135680 + }, + { + "epoch": 1.02, + "learning_rate": 4.777025517521062e-05, + "loss": 4.0532, + "step": 136192 + }, + { + "epoch": 1.02, + "learning_rate": 4.77618692277001e-05, + "loss": 4.048, + "step": 136704 + }, + { + "epoch": 1.02, + "learning_rate": 4.775348328018958e-05, + "loss": 4.0512, + "step": 137216 + }, + { + "epoch": 1.02, + "learning_rate": 4.774509733267906e-05, + "loss": 4.0502, + "step": 137728 + }, + { + "epoch": 1.02, + "learning_rate": 4.773671138516854e-05, + "loss": 4.0467, + "step": 138240 + }, + { + "epoch": 1.02, + "learning_rate": 4.772832543765802e-05, + "loss": 4.046, + "step": 138752 + }, + { + "epoch": 1.02, + "learning_rate": 4.77199394901475e-05, + "loss": 4.0423, + "step": 139264 + }, + { + "epoch": 1.02, + "learning_rate": 4.771155354263698e-05, + "loss": 4.0469, + "step": 139776 + }, + { + "epoch": 1.02, + "learning_rate": 4.7703183973930186e-05, + "loss": 4.035, + "step": 140288 + }, + { + "epoch": 1.02, + "learning_rate": 4.7694798026419666e-05, + "loss": 4.0426, + "step": 140800 + }, + { + "epoch": 1.02, + "learning_rate": 4.7686412078909146e-05, + "loss": 4.0393, + "step": 141312 + }, + { + "epoch": 1.02, + "learning_rate": 4.7678042510202355e-05, + "loss": 4.0414, + "step": 141824 + }, + { + "epoch": 1.02, + "learning_rate": 4.766965656269184e-05, + "loss": 4.0281, + "step": 142336 + }, + { + "epoch": 1.02, + "learning_rate": 4.766127061518132e-05, + "loss": 4.0519, + "step": 142848 + }, + { + "epoch": 1.02, + "learning_rate": 4.76528846676708e-05, + "loss": 4.0558, + "step": 143360 + }, + { + "epoch": 1.02, + "learning_rate": 4.764451509896401e-05, + "loss": 4.0378, + "step": 143872 + }, + { + "epoch": 1.02, + "learning_rate": 4.763612915145349e-05, + "loss": 4.0316, + "step": 144384 + }, + { + "epoch": 1.02, + "learning_rate": 4.762774320394297e-05, + "loss": 4.0392, + "step": 144896 + }, + { + "epoch": 1.02, + "learning_rate": 4.761935725643245e-05, + "loss": 4.0414, + "step": 145408 + }, + { + "epoch": 1.02, + "learning_rate": 4.761098768772566e-05, + "loss": 4.042, + "step": 145920 + }, + { + "epoch": 1.02, + "learning_rate": 4.760260174021514e-05, + "loss": 4.038, + "step": 146432 + }, + { + "epoch": 1.02, + "learning_rate": 4.759421579270462e-05, + "loss": 4.0379, + "step": 146944 + }, + { + "epoch": 1.02, + "learning_rate": 4.758584622399783e-05, + "loss": 4.0331, + "step": 147456 + }, + { + "epoch": 1.02, + "learning_rate": 4.757746027648731e-05, + "loss": 4.0389, + "step": 147968 + }, + { + "epoch": 1.02, + "learning_rate": 4.7569074328976796e-05, + "loss": 4.0273, + "step": 148480 + }, + { + "epoch": 1.02, + "learning_rate": 4.7560688381466276e-05, + "loss": 4.0357, + "step": 148992 + }, + { + "epoch": 1.02, + "learning_rate": 4.7552302433955756e-05, + "loss": 4.0321, + "step": 149504 + }, + { + "epoch": 1.02, + "learning_rate": 4.7543932865248965e-05, + "loss": 4.0209, + "step": 150016 + }, + { + "epoch": 1.02, + "learning_rate": 4.7535546917738445e-05, + "loss": 4.0379, + "step": 150528 + }, + { + "epoch": 1.02, + "learning_rate": 4.7527160970227925e-05, + "loss": 4.0249, + "step": 151040 + }, + { + "epoch": 1.02, + "learning_rate": 4.7518775022717405e-05, + "loss": 4.0343, + "step": 151552 + }, + { + "epoch": 1.02, + "learning_rate": 4.7510389075206885e-05, + "loss": 4.0203, + "step": 152064 + }, + { + "epoch": 1.02, + "learning_rate": 4.7502003127696365e-05, + "loss": 4.021, + "step": 152576 + }, + { + "epoch": 1.03, + "eval_loss": 4.025944232940674, + "eval_runtime": 312.8015, + "eval_samples_per_second": 1219.914, + "eval_steps_per_second": 38.123, + "step": 152640 + }, + { + "epoch": 0.0, + "learning_rate": 4.7493617180185845e-05, + "loss": 4.0152, + "step": 153088 + }, + { + "epoch": 0.0, + "learning_rate": 4.748523123267532e-05, + "loss": 4.0082, + "step": 153600 + }, + { + "epoch": 0.0, + "learning_rate": 4.74768452851648e-05, + "loss": 4.0288, + "step": 154112 + }, + { + "epoch": 0.0, + "learning_rate": 4.746845933765428e-05, + "loss": 4.0195, + "step": 154624 + }, + { + "epoch": 0.0, + "learning_rate": 4.7460073390143764e-05, + "loss": 4.0285, + "step": 155136 + }, + { + "epoch": 0.0, + "learning_rate": 4.7451687442633244e-05, + "loss": 4.0096, + "step": 155648 + }, + { + "epoch": 0.0, + "learning_rate": 4.7443301495122724e-05, + "loss": 4.0167, + "step": 156160 + }, + { + "epoch": 0.0, + "learning_rate": 4.7434915547612204e-05, + "loss": 4.0008, + "step": 156672 + }, + { + "epoch": 0.0, + "learning_rate": 4.7426529600101684e-05, + "loss": 4.0183, + "step": 157184 + }, + { + "epoch": 0.0, + "learning_rate": 4.7418143652591164e-05, + "loss": 4.0191, + "step": 157696 + }, + { + "epoch": 0.0, + "learning_rate": 4.7409757705080644e-05, + "loss": 4.0196, + "step": 158208 + }, + { + "epoch": 0.0, + "learning_rate": 4.740138813637385e-05, + "loss": 4.0122, + "step": 158720 + }, + { + "epoch": 0.0, + "learning_rate": 4.739301856766706e-05, + "loss": 4.004, + "step": 159232 + }, + { + "epoch": 0.0, + "learning_rate": 4.738463262015654e-05, + "loss": 4.0029, + "step": 159744 + }, + { + "epoch": 0.0, + "learning_rate": 4.737624667264602e-05, + "loss": 3.9995, + "step": 160256 + }, + { + "epoch": 0.0, + "learning_rate": 4.73678607251355e-05, + "loss": 4.0008, + "step": 160768 + }, + { + "epoch": 0.0, + "learning_rate": 4.735947477762498e-05, + "loss": 4.0031, + "step": 161280 + }, + { + "epoch": 0.0, + "learning_rate": 4.735108883011446e-05, + "loss": 3.9981, + "step": 161792 + }, + { + "epoch": 0.0, + "learning_rate": 4.734270288260394e-05, + "loss": 3.9991, + "step": 162304 + }, + { + "epoch": 0.0, + "learning_rate": 4.733433331389716e-05, + "loss": 4.0189, + "step": 162816 + }, + { + "epoch": 0.0, + "learning_rate": 4.732594736638664e-05, + "loss": 4.0015, + "step": 163328 + }, + { + "epoch": 0.0, + "learning_rate": 4.731756141887612e-05, + "loss": 4.0076, + "step": 163840 + }, + { + "epoch": 0.0, + "learning_rate": 4.730919185016933e-05, + "loss": 3.9948, + "step": 164352 + }, + { + "epoch": 0.0, + "learning_rate": 4.730080590265881e-05, + "loss": 4.0107, + "step": 164864 + }, + { + "epoch": 0.0, + "learning_rate": 4.729241995514829e-05, + "loss": 3.9874, + "step": 165376 + }, + { + "epoch": 0.0, + "learning_rate": 4.728403400763777e-05, + "loss": 3.9989, + "step": 165888 + }, + { + "epoch": 0.0, + "learning_rate": 4.727564806012725e-05, + "loss": 3.9967, + "step": 166400 + }, + { + "epoch": 0.0, + "learning_rate": 4.726726211261673e-05, + "loss": 3.9934, + "step": 166912 + }, + { + "epoch": 0.0, + "learning_rate": 4.7258892543909936e-05, + "loss": 3.9809, + "step": 167424 + }, + { + "epoch": 0.01, + "learning_rate": 4.7250506596399416e-05, + "loss": 3.9872, + "step": 167936 + }, + { + "epoch": 0.01, + "learning_rate": 4.7242120648888896e-05, + "loss": 3.9963, + "step": 168448 + }, + { + "epoch": 0.01, + "learning_rate": 4.723373470137838e-05, + "loss": 3.9972, + "step": 168960 + }, + { + "epoch": 0.01, + "learning_rate": 4.7225348753867856e-05, + "loss": 3.9931, + "step": 169472 + }, + { + "epoch": 0.01, + "learning_rate": 4.7216962806357336e-05, + "loss": 3.9947, + "step": 169984 + }, + { + "epoch": 0.01, + "learning_rate": 4.7208576858846816e-05, + "loss": 3.9912, + "step": 170496 + }, + { + "epoch": 0.01, + "learning_rate": 4.7200190911336296e-05, + "loss": 3.9972, + "step": 171008 + }, + { + "epoch": 0.01, + "learning_rate": 4.7191821342629505e-05, + "loss": 3.9815, + "step": 171520 + }, + { + "epoch": 0.01, + "learning_rate": 4.7183435395118985e-05, + "loss": 3.9819, + "step": 172032 + }, + { + "epoch": 0.01, + "learning_rate": 4.7175049447608465e-05, + "loss": 3.9722, + "step": 172544 + }, + { + "epoch": 0.01, + "learning_rate": 4.716667987890168e-05, + "loss": 3.9896, + "step": 173056 + }, + { + "epoch": 0.01, + "learning_rate": 4.7158293931391154e-05, + "loss": 3.9758, + "step": 173568 + }, + { + "epoch": 0.01, + "learning_rate": 4.7149907983880634e-05, + "loss": 3.9858, + "step": 174080 + }, + { + "epoch": 0.01, + "learning_rate": 4.714152203637012e-05, + "loss": 3.9783, + "step": 174592 + }, + { + "epoch": 0.01, + "learning_rate": 4.71331360888596e-05, + "loss": 3.9749, + "step": 175104 + }, + { + "epoch": 0.01, + "learning_rate": 4.712476652015281e-05, + "loss": 3.9874, + "step": 175616 + }, + { + "epoch": 0.01, + "learning_rate": 4.711638057264229e-05, + "loss": 3.9756, + "step": 176128 + }, + { + "epoch": 0.01, + "learning_rate": 4.710799462513177e-05, + "loss": 3.9774, + "step": 176640 + }, + { + "epoch": 0.01, + "learning_rate": 4.709960867762125e-05, + "loss": 3.9596, + "step": 177152 + }, + { + "epoch": 0.01, + "learning_rate": 4.709122273011073e-05, + "loss": 3.9712, + "step": 177664 + }, + { + "epoch": 0.01, + "learning_rate": 4.708283678260021e-05, + "loss": 3.9803, + "step": 178176 + }, + { + "epoch": 0.01, + "learning_rate": 4.707445083508969e-05, + "loss": 3.9751, + "step": 178688 + }, + { + "epoch": 0.01, + "learning_rate": 4.70660812663829e-05, + "loss": 3.9738, + "step": 179200 + }, + { + "epoch": 0.01, + "learning_rate": 4.705769531887238e-05, + "loss": 3.9593, + "step": 179712 + }, + { + "epoch": 0.01, + "learning_rate": 4.704930937136186e-05, + "loss": 3.9722, + "step": 180224 + }, + { + "epoch": 0.01, + "learning_rate": 4.704092342385134e-05, + "loss": 3.9577, + "step": 180736 + }, + { + "epoch": 0.01, + "learning_rate": 4.703253747634082e-05, + "loss": 3.9814, + "step": 181248 + }, + { + "epoch": 0.01, + "learning_rate": 4.7024151528830305e-05, + "loss": 3.955, + "step": 181760 + }, + { + "epoch": 0.01, + "learning_rate": 4.7015781960123514e-05, + "loss": 3.9744, + "step": 182272 + }, + { + "epoch": 0.01, + "learning_rate": 4.7007396012612994e-05, + "loss": 3.972, + "step": 182784 + }, + { + "epoch": 0.01, + "learning_rate": 4.6999010065102474e-05, + "loss": 3.953, + "step": 183296 + }, + { + "epoch": 0.01, + "learning_rate": 4.6990624117591954e-05, + "loss": 3.963, + "step": 183808 + }, + { + "epoch": 0.01, + "learning_rate": 4.6982238170081434e-05, + "loss": 3.9669, + "step": 184320 + }, + { + "epoch": 0.01, + "learning_rate": 4.6973852222570914e-05, + "loss": 3.953, + "step": 184832 + }, + { + "epoch": 0.01, + "learning_rate": 4.696548265386412e-05, + "loss": 3.9589, + "step": 185344 + }, + { + "epoch": 0.01, + "learning_rate": 4.69570967063536e-05, + "loss": 3.9676, + "step": 185856 + }, + { + "epoch": 0.01, + "learning_rate": 4.694871075884308e-05, + "loss": 3.964, + "step": 186368 + }, + { + "epoch": 0.01, + "learning_rate": 4.694032481133256e-05, + "loss": 3.9518, + "step": 186880 + }, + { + "epoch": 0.01, + "learning_rate": 4.693193886382204e-05, + "loss": 3.9563, + "step": 187392 + }, + { + "epoch": 0.01, + "learning_rate": 4.692355291631152e-05, + "loss": 3.9486, + "step": 187904 + }, + { + "epoch": 0.01, + "learning_rate": 4.6915166968801e-05, + "loss": 3.9609, + "step": 188416 + }, + { + "epoch": 0.01, + "learning_rate": 4.690678102129048e-05, + "loss": 3.9739, + "step": 188928 + }, + { + "epoch": 0.01, + "learning_rate": 4.689842783138743e-05, + "loss": 3.9575, + "step": 189440 + }, + { + "epoch": 0.01, + "learning_rate": 4.689004188387691e-05, + "loss": 3.9697, + "step": 189952 + }, + { + "epoch": 0.01, + "learning_rate": 4.688165593636639e-05, + "loss": 3.968, + "step": 190464 + }, + { + "epoch": 0.01, + "learning_rate": 4.687326998885587e-05, + "loss": 3.9614, + "step": 190976 + }, + { + "epoch": 0.01, + "learning_rate": 4.686488404134534e-05, + "loss": 3.9488, + "step": 191488 + }, + { + "epoch": 0.01, + "learning_rate": 4.6856514472638556e-05, + "loss": 3.9646, + "step": 192000 + }, + { + "epoch": 0.01, + "learning_rate": 4.6848128525128036e-05, + "loss": 3.9557, + "step": 192512 + }, + { + "epoch": 0.01, + "learning_rate": 4.683974257761751e-05, + "loss": 3.9564, + "step": 193024 + }, + { + "epoch": 0.01, + "learning_rate": 4.6831356630106996e-05, + "loss": 3.9518, + "step": 193536 + }, + { + "epoch": 0.01, + "learning_rate": 4.6822970682596476e-05, + "loss": 3.9574, + "step": 194048 + }, + { + "epoch": 0.01, + "learning_rate": 4.681460111388969e-05, + "loss": 3.9695, + "step": 194560 + }, + { + "epoch": 0.01, + "learning_rate": 4.6806215166379165e-05, + "loss": 3.9526, + "step": 195072 + }, + { + "epoch": 0.01, + "learning_rate": 4.6797829218868645e-05, + "loss": 3.9405, + "step": 195584 + }, + { + "epoch": 0.01, + "learning_rate": 4.6789443271358125e-05, + "loss": 3.9459, + "step": 196096 + }, + { + "epoch": 0.01, + "learning_rate": 4.6781057323847605e-05, + "loss": 3.9561, + "step": 196608 + }, + { + "epoch": 0.01, + "learning_rate": 4.6772671376337085e-05, + "loss": 3.9559, + "step": 197120 + }, + { + "epoch": 0.01, + "learning_rate": 4.6764285428826565e-05, + "loss": 3.9581, + "step": 197632 + }, + { + "epoch": 0.01, + "learning_rate": 4.6755915860119774e-05, + "loss": 3.9426, + "step": 198144 + }, + { + "epoch": 0.02, + "learning_rate": 4.6747529912609254e-05, + "loss": 3.9461, + "step": 198656 + }, + { + "epoch": 0.02, + "learning_rate": 4.6739143965098734e-05, + "loss": 3.9371, + "step": 199168 + }, + { + "epoch": 0.02, + "learning_rate": 4.6730758017588214e-05, + "loss": 3.943, + "step": 199680 + }, + { + "epoch": 0.02, + "learning_rate": 4.672238844888143e-05, + "loss": 3.9485, + "step": 200192 + }, + { + "epoch": 0.02, + "learning_rate": 4.671400250137091e-05, + "loss": 3.9487, + "step": 200704 + }, + { + "epoch": 0.02, + "learning_rate": 4.670561655386039e-05, + "loss": 3.9659, + "step": 201216 + }, + { + "epoch": 0.02, + "learning_rate": 4.669723060634987e-05, + "loss": 3.9461, + "step": 201728 + }, + { + "epoch": 0.02, + "learning_rate": 4.668884465883935e-05, + "loss": 3.9381, + "step": 202240 + }, + { + "epoch": 0.02, + "learning_rate": 4.668045871132883e-05, + "loss": 3.9426, + "step": 202752 + }, + { + "epoch": 0.02, + "learning_rate": 4.667207276381831e-05, + "loss": 3.9435, + "step": 203264 + }, + { + "epoch": 0.02, + "learning_rate": 4.666370319511152e-05, + "loss": 3.9499, + "step": 203776 + }, + { + "epoch": 0.02, + "learning_rate": 4.6655317247601e-05, + "loss": 3.9459, + "step": 204288 + }, + { + "epoch": 0.02, + "learning_rate": 4.664693130009048e-05, + "loss": 3.9419, + "step": 204800 + }, + { + "epoch": 0.02, + "learning_rate": 4.663854535257996e-05, + "loss": 3.9377, + "step": 205312 + }, + { + "epoch": 0.02, + "learning_rate": 4.663015940506944e-05, + "loss": 3.9463, + "step": 205824 + }, + { + "epoch": 0.02, + "learning_rate": 4.662177345755892e-05, + "loss": 3.9211, + "step": 206336 + }, + { + "epoch": 0.02, + "learning_rate": 4.661340388885213e-05, + "loss": 3.9387, + "step": 206848 + }, + { + "epoch": 0.02, + "learning_rate": 4.6605017941341614e-05, + "loss": 3.9345, + "step": 207360 + }, + { + "epoch": 0.02, + "learning_rate": 4.6596631993831094e-05, + "loss": 3.9378, + "step": 207872 + }, + { + "epoch": 0.02, + "learning_rate": 4.6588246046320574e-05, + "loss": 3.9303, + "step": 208384 + }, + { + "epoch": 0.02, + "learning_rate": 4.657987647761378e-05, + "loss": 3.9396, + "step": 208896 + }, + { + "epoch": 0.02, + "learning_rate": 4.657149053010326e-05, + "loss": 3.925, + "step": 209408 + }, + { + "epoch": 0.02, + "learning_rate": 4.656310458259274e-05, + "loss": 3.931, + "step": 209920 + }, + { + "epoch": 0.02, + "learning_rate": 4.655471863508222e-05, + "loss": 3.9383, + "step": 210432 + }, + { + "epoch": 0.02, + "learning_rate": 4.65463326875717e-05, + "loss": 3.9313, + "step": 210944 + }, + { + "epoch": 0.02, + "learning_rate": 4.653796311886491e-05, + "loss": 3.9512, + "step": 211456 + }, + { + "epoch": 0.02, + "learning_rate": 4.652957717135439e-05, + "loss": 3.9432, + "step": 211968 + }, + { + "epoch": 0.02, + "learning_rate": 4.652119122384387e-05, + "loss": 3.9377, + "step": 212480 + }, + { + "epoch": 0.02, + "learning_rate": 4.651280527633335e-05, + "loss": 3.9264, + "step": 212992 + }, + { + "epoch": 0.02, + "learning_rate": 4.650443570762657e-05, + "loss": 3.9306, + "step": 213504 + }, + { + "epoch": 0.02, + "learning_rate": 4.649604976011605e-05, + "loss": 3.9343, + "step": 214016 + }, + { + "epoch": 0.02, + "learning_rate": 4.648766381260553e-05, + "loss": 3.931, + "step": 214528 + }, + { + "epoch": 0.02, + "learning_rate": 4.6479277865095e-05, + "loss": 3.9295, + "step": 215040 + }, + { + "epoch": 0.02, + "learning_rate": 4.647090829638822e-05, + "loss": 3.9216, + "step": 215552 + }, + { + "epoch": 0.02, + "learning_rate": 4.64625223488777e-05, + "loss": 3.9317, + "step": 216064 + }, + { + "epoch": 0.02, + "learning_rate": 4.645413640136718e-05, + "loss": 3.9188, + "step": 216576 + }, + { + "epoch": 0.02, + "learning_rate": 4.644575045385665e-05, + "loss": 3.9276, + "step": 217088 + }, + { + "epoch": 0.02, + "learning_rate": 4.643736450634613e-05, + "loss": 3.9241, + "step": 217600 + }, + { + "epoch": 0.02, + "learning_rate": 4.6428994937639346e-05, + "loss": 3.9254, + "step": 218112 + }, + { + "epoch": 0.02, + "learning_rate": 4.642060899012882e-05, + "loss": 3.9145, + "step": 218624 + }, + { + "epoch": 0.02, + "learning_rate": 4.6412223042618306e-05, + "loss": 3.9399, + "step": 219136 + }, + { + "epoch": 0.02, + "learning_rate": 4.6403837095107786e-05, + "loss": 3.9408, + "step": 219648 + }, + { + "epoch": 0.02, + "learning_rate": 4.6395467526401e-05, + "loss": 3.9287, + "step": 220160 + }, + { + "epoch": 0.02, + "learning_rate": 4.6387081578890475e-05, + "loss": 3.9144, + "step": 220672 + }, + { + "epoch": 0.02, + "learning_rate": 4.6378695631379955e-05, + "loss": 3.9268, + "step": 221184 + }, + { + "epoch": 0.02, + "learning_rate": 4.6370309683869435e-05, + "loss": 3.9281, + "step": 221696 + }, + { + "epoch": 0.02, + "learning_rate": 4.6361923736358915e-05, + "loss": 3.9319, + "step": 222208 + }, + { + "epoch": 0.02, + "learning_rate": 4.6353554167652124e-05, + "loss": 3.9251, + "step": 222720 + }, + { + "epoch": 0.02, + "learning_rate": 4.6345168220141604e-05, + "loss": 3.9242, + "step": 223232 + }, + { + "epoch": 0.02, + "learning_rate": 4.6336782272631084e-05, + "loss": 3.9244, + "step": 223744 + }, + { + "epoch": 0.02, + "learning_rate": 4.6328396325120564e-05, + "loss": 3.9314, + "step": 224256 + }, + { + "epoch": 0.02, + "learning_rate": 4.6320010377610043e-05, + "loss": 3.9206, + "step": 224768 + }, + { + "epoch": 0.02, + "learning_rate": 4.631164080890326e-05, + "loss": 3.9259, + "step": 225280 + }, + { + "epoch": 0.02, + "learning_rate": 4.630325486139274e-05, + "loss": 3.9222, + "step": 225792 + }, + { + "epoch": 0.02, + "learning_rate": 4.629486891388222e-05, + "loss": 3.914, + "step": 226304 + }, + { + "epoch": 0.02, + "learning_rate": 4.62864829663717e-05, + "loss": 3.9269, + "step": 226816 + }, + { + "epoch": 0.02, + "learning_rate": 4.627811339766491e-05, + "loss": 3.9242, + "step": 227328 + }, + { + "epoch": 0.02, + "learning_rate": 4.626972745015439e-05, + "loss": 3.9223, + "step": 227840 + }, + { + "epoch": 0.02, + "learning_rate": 4.626134150264387e-05, + "loss": 3.9137, + "step": 228352 + }, + { + "epoch": 0.02, + "learning_rate": 4.625295555513335e-05, + "loss": 3.9128, + "step": 228864 + }, + { + "epoch": 0.03, + "eval_loss": 3.951106309890747, + "eval_runtime": 307.338, + "eval_samples_per_second": 1241.6, + "eval_steps_per_second": 38.801, + "step": 228960 + }, + { + "epoch": 1.0, + "learning_rate": 4.624456960762283e-05, + "loss": 3.9148, + "step": 229376 + }, + { + "epoch": 1.0, + "learning_rate": 4.623620003891604e-05, + "loss": 3.9056, + "step": 229888 + }, + { + "epoch": 1.0, + "learning_rate": 4.622781409140552e-05, + "loss": 3.9222, + "step": 230400 + }, + { + "epoch": 1.0, + "learning_rate": 4.6219428143895e-05, + "loss": 3.9141, + "step": 230912 + }, + { + "epoch": 1.0, + "learning_rate": 4.621104219638448e-05, + "loss": 3.9257, + "step": 231424 + }, + { + "epoch": 1.0, + "learning_rate": 4.620267262767769e-05, + "loss": 3.9068, + "step": 231936 + }, + { + "epoch": 1.0, + "learning_rate": 4.619428668016717e-05, + "loss": 3.9103, + "step": 232448 + }, + { + "epoch": 1.0, + "learning_rate": 4.618590073265665e-05, + "loss": 3.8988, + "step": 232960 + }, + { + "epoch": 1.0, + "learning_rate": 4.617751478514613e-05, + "loss": 3.9153, + "step": 233472 + }, + { + "epoch": 1.0, + "learning_rate": 4.616912883763561e-05, + "loss": 3.9135, + "step": 233984 + }, + { + "epoch": 1.0, + "learning_rate": 4.616075926892882e-05, + "loss": 3.9169, + "step": 234496 + }, + { + "epoch": 1.0, + "learning_rate": 4.61523733214183e-05, + "loss": 3.9094, + "step": 235008 + }, + { + "epoch": 1.0, + "learning_rate": 4.614398737390778e-05, + "loss": 3.9027, + "step": 235520 + }, + { + "epoch": 1.0, + "learning_rate": 4.613560142639726e-05, + "loss": 3.9024, + "step": 236032 + }, + { + "epoch": 1.0, + "learning_rate": 4.612721547888674e-05, + "loss": 3.8978, + "step": 236544 + }, + { + "epoch": 1.0, + "learning_rate": 4.611884591017995e-05, + "loss": 3.9008, + "step": 237056 + }, + { + "epoch": 1.0, + "learning_rate": 4.611045996266943e-05, + "loss": 3.9021, + "step": 237568 + }, + { + "epoch": 1.0, + "learning_rate": 4.610207401515891e-05, + "loss": 3.8975, + "step": 238080 + }, + { + "epoch": 1.0, + "learning_rate": 4.609368806764839e-05, + "loss": 3.8975, + "step": 238592 + }, + { + "epoch": 1.0, + "learning_rate": 4.608530212013788e-05, + "loss": 3.9214, + "step": 239104 + }, + { + "epoch": 1.0, + "learning_rate": 4.6076932551431087e-05, + "loss": 3.9018, + "step": 239616 + }, + { + "epoch": 1.0, + "learning_rate": 4.6068546603920566e-05, + "loss": 3.9045, + "step": 240128 + }, + { + "epoch": 1.0, + "learning_rate": 4.6060160656410046e-05, + "loss": 3.8985, + "step": 240640 + }, + { + "epoch": 1.0, + "learning_rate": 4.6051774708899526e-05, + "loss": 3.9081, + "step": 241152 + }, + { + "epoch": 1.0, + "learning_rate": 4.6043405140192735e-05, + "loss": 3.8913, + "step": 241664 + }, + { + "epoch": 1.0, + "learning_rate": 4.6035019192682215e-05, + "loss": 3.906, + "step": 242176 + }, + { + "epoch": 1.0, + "learning_rate": 4.6026633245171695e-05, + "loss": 3.897, + "step": 242688 + }, + { + "epoch": 1.0, + "learning_rate": 4.6018247297661175e-05, + "loss": 3.8936, + "step": 243200 + }, + { + "epoch": 1.0, + "learning_rate": 4.6009877728954384e-05, + "loss": 3.8808, + "step": 243712 + }, + { + "epoch": 1.01, + "learning_rate": 4.6001491781443864e-05, + "loss": 3.8913, + "step": 244224 + }, + { + "epoch": 1.01, + "learning_rate": 4.5993105833933344e-05, + "loss": 3.8972, + "step": 244736 + }, + { + "epoch": 1.01, + "learning_rate": 4.598471988642283e-05, + "loss": 3.9008, + "step": 245248 + }, + { + "epoch": 1.01, + "learning_rate": 4.597635031771604e-05, + "loss": 3.9015, + "step": 245760 + }, + { + "epoch": 1.01, + "learning_rate": 4.596796437020552e-05, + "loss": 3.8986, + "step": 246272 + }, + { + "epoch": 1.01, + "learning_rate": 4.5959578422695e-05, + "loss": 3.8896, + "step": 246784 + }, + { + "epoch": 1.01, + "learning_rate": 4.595119247518448e-05, + "loss": 3.9044, + "step": 247296 + }, + { + "epoch": 1.01, + "learning_rate": 4.594282290647769e-05, + "loss": 3.8846, + "step": 247808 + }, + { + "epoch": 1.01, + "learning_rate": 4.593443695896717e-05, + "loss": 3.8915, + "step": 248320 + }, + { + "epoch": 1.01, + "learning_rate": 4.592605101145665e-05, + "loss": 3.8767, + "step": 248832 + }, + { + "epoch": 1.01, + "learning_rate": 4.591766506394613e-05, + "loss": 3.8927, + "step": 249344 + }, + { + "epoch": 1.01, + "learning_rate": 4.590929549523934e-05, + "loss": 3.8842, + "step": 249856 + }, + { + "epoch": 1.01, + "learning_rate": 4.590090954772882e-05, + "loss": 3.8934, + "step": 250368 + }, + { + "epoch": 1.01, + "learning_rate": 4.58925236002183e-05, + "loss": 3.8895, + "step": 250880 + }, + { + "epoch": 1.01, + "learning_rate": 4.5884137652707785e-05, + "loss": 3.8803, + "step": 251392 + }, + { + "epoch": 1.01, + "learning_rate": 4.587575170519726e-05, + "loss": 3.8951, + "step": 251904 + }, + { + "epoch": 1.01, + "learning_rate": 4.5867382136490474e-05, + "loss": 3.8847, + "step": 252416 + }, + { + "epoch": 1.01, + "learning_rate": 4.5858996188979954e-05, + "loss": 3.8823, + "step": 252928 + }, + { + "epoch": 1.01, + "learning_rate": 4.585061024146943e-05, + "loss": 3.8693, + "step": 253440 + }, + { + "epoch": 1.01, + "learning_rate": 4.584222429395891e-05, + "loss": 3.8783, + "step": 253952 + }, + { + "epoch": 1.01, + "learning_rate": 4.583383834644839e-05, + "loss": 3.8902, + "step": 254464 + }, + { + "epoch": 1.01, + "learning_rate": 4.58254687777416e-05, + "loss": 3.8851, + "step": 254976 + }, + { + "epoch": 1.01, + "learning_rate": 4.5817082830231076e-05, + "loss": 3.8829, + "step": 255488 + }, + { + "epoch": 1.01, + "learning_rate": 4.5808696882720556e-05, + "loss": 3.871, + "step": 256000 + }, + { + "epoch": 1.01, + "learning_rate": 4.5800310935210036e-05, + "loss": 3.8829, + "step": 256512 + }, + { + "epoch": 1.01, + "learning_rate": 4.579194136650325e-05, + "loss": 3.8675, + "step": 257024 + }, + { + "epoch": 1.01, + "learning_rate": 4.578355541899273e-05, + "loss": 3.8869, + "step": 257536 + }, + { + "epoch": 1.01, + "learning_rate": 4.577516947148221e-05, + "loss": 3.872, + "step": 258048 + }, + { + "epoch": 1.01, + "learning_rate": 4.576678352397169e-05, + "loss": 3.8795, + "step": 258560 + }, + { + "epoch": 1.01, + "learning_rate": 4.57584139552649e-05, + "loss": 3.8841, + "step": 259072 + }, + { + "epoch": 1.01, + "learning_rate": 4.575002800775438e-05, + "loss": 3.8673, + "step": 259584 + }, + { + "epoch": 1.01, + "learning_rate": 4.574164206024386e-05, + "loss": 3.8718, + "step": 260096 + }, + { + "epoch": 1.01, + "learning_rate": 4.573325611273334e-05, + "loss": 3.8785, + "step": 260608 + }, + { + "epoch": 1.01, + "learning_rate": 4.572487016522282e-05, + "loss": 3.865, + "step": 261120 + }, + { + "epoch": 1.01, + "learning_rate": 4.571650059651603e-05, + "loss": 3.8738, + "step": 261632 + }, + { + "epoch": 1.01, + "learning_rate": 4.570811464900551e-05, + "loss": 3.8762, + "step": 262144 + }, + { + "epoch": 1.01, + "learning_rate": 4.569972870149499e-05, + "loss": 3.8798, + "step": 262656 + }, + { + "epoch": 1.01, + "learning_rate": 4.5691342753984476e-05, + "loss": 3.8647, + "step": 263168 + }, + { + "epoch": 1.01, + "learning_rate": 4.5682973185277685e-05, + "loss": 3.8704, + "step": 263680 + }, + { + "epoch": 1.01, + "learning_rate": 4.5674587237767165e-05, + "loss": 3.861, + "step": 264192 + }, + { + "epoch": 1.01, + "learning_rate": 4.5666201290256645e-05, + "loss": 3.8716, + "step": 264704 + }, + { + "epoch": 1.01, + "learning_rate": 4.5657815342746125e-05, + "loss": 3.8828, + "step": 265216 + }, + { + "epoch": 1.01, + "learning_rate": 4.5649445774039334e-05, + "loss": 3.8733, + "step": 265728 + }, + { + "epoch": 1.01, + "learning_rate": 4.5641059826528814e-05, + "loss": 3.8848, + "step": 266240 + }, + { + "epoch": 1.01, + "learning_rate": 4.5632673879018294e-05, + "loss": 3.8836, + "step": 266752 + }, + { + "epoch": 1.01, + "learning_rate": 4.5624287931507774e-05, + "loss": 3.8812, + "step": 267264 + }, + { + "epoch": 1.01, + "learning_rate": 4.561591836280098e-05, + "loss": 3.8599, + "step": 267776 + }, + { + "epoch": 1.01, + "learning_rate": 4.560753241529046e-05, + "loss": 3.8781, + "step": 268288 + }, + { + "epoch": 1.01, + "learning_rate": 4.559914646777994e-05, + "loss": 3.8771, + "step": 268800 + }, + { + "epoch": 1.01, + "learning_rate": 4.559076052026943e-05, + "loss": 3.867, + "step": 269312 + }, + { + "epoch": 1.01, + "learning_rate": 4.558239095156264e-05, + "loss": 3.872, + "step": 269824 + }, + { + "epoch": 1.01, + "learning_rate": 4.557400500405212e-05, + "loss": 3.8748, + "step": 270336 + }, + { + "epoch": 1.01, + "learning_rate": 4.55656190565416e-05, + "loss": 3.8861, + "step": 270848 + }, + { + "epoch": 1.01, + "learning_rate": 4.555723310903108e-05, + "loss": 3.8684, + "step": 271360 + }, + { + "epoch": 1.01, + "learning_rate": 4.554886354032429e-05, + "loss": 3.8562, + "step": 271872 + }, + { + "epoch": 1.01, + "learning_rate": 4.554047759281377e-05, + "loss": 3.8665, + "step": 272384 + }, + { + "epoch": 1.01, + "learning_rate": 4.553209164530325e-05, + "loss": 3.8689, + "step": 272896 + }, + { + "epoch": 1.01, + "learning_rate": 4.552370569779273e-05, + "loss": 3.8735, + "step": 273408 + }, + { + "epoch": 1.01, + "learning_rate": 4.551533612908594e-05, + "loss": 3.8738, + "step": 273920 + }, + { + "epoch": 1.01, + "learning_rate": 4.550695018157542e-05, + "loss": 3.8629, + "step": 274432 + }, + { + "epoch": 1.02, + "learning_rate": 4.54985642340649e-05, + "loss": 3.8656, + "step": 274944 + }, + { + "epoch": 1.02, + "learning_rate": 4.5490178286554384e-05, + "loss": 3.8555, + "step": 275456 + }, + { + "epoch": 1.02, + "learning_rate": 4.548180871784759e-05, + "loss": 3.8606, + "step": 275968 + }, + { + "epoch": 1.02, + "learning_rate": 4.547342277033707e-05, + "loss": 3.8611, + "step": 276480 + }, + { + "epoch": 1.02, + "learning_rate": 4.546503682282655e-05, + "loss": 3.8743, + "step": 276992 + }, + { + "epoch": 1.02, + "learning_rate": 4.545665087531603e-05, + "loss": 3.8857, + "step": 277504 + }, + { + "epoch": 1.02, + "learning_rate": 4.544828130660924e-05, + "loss": 3.862, + "step": 278016 + }, + { + "epoch": 1.02, + "learning_rate": 4.543989535909872e-05, + "loss": 3.8545, + "step": 278528 + }, + { + "epoch": 1.02, + "learning_rate": 4.54315094115882e-05, + "loss": 3.8642, + "step": 279040 + }, + { + "epoch": 1.02, + "learning_rate": 4.542312346407768e-05, + "loss": 3.8616, + "step": 279552 + }, + { + "epoch": 1.02, + "learning_rate": 4.541475389537089e-05, + "loss": 3.8731, + "step": 280064 + }, + { + "epoch": 1.02, + "learning_rate": 4.540636794786037e-05, + "loss": 3.8625, + "step": 280576 + }, + { + "epoch": 1.02, + "learning_rate": 4.539798200034985e-05, + "loss": 3.8651, + "step": 281088 + }, + { + "epoch": 1.02, + "learning_rate": 4.538959605283933e-05, + "loss": 3.8589, + "step": 281600 + }, + { + "epoch": 1.02, + "learning_rate": 4.5381226484132546e-05, + "loss": 3.8696, + "step": 282112 + }, + { + "epoch": 1.02, + "learning_rate": 4.5372840536622026e-05, + "loss": 3.8422, + "step": 282624 + }, + { + "epoch": 1.02, + "learning_rate": 4.5364454589111506e-05, + "loss": 3.8566, + "step": 283136 + }, + { + "epoch": 1.02, + "learning_rate": 4.5356068641600986e-05, + "loss": 3.8522, + "step": 283648 + }, + { + "epoch": 1.02, + "learning_rate": 4.5347699072894195e-05, + "loss": 3.8643, + "step": 284160 + }, + { + "epoch": 1.02, + "learning_rate": 4.5339313125383675e-05, + "loss": 3.8503, + "step": 284672 + }, + { + "epoch": 1.02, + "learning_rate": 4.5330927177873155e-05, + "loss": 3.8594, + "step": 285184 + }, + { + "epoch": 1.02, + "learning_rate": 4.5322541230362635e-05, + "loss": 3.8493, + "step": 285696 + }, + { + "epoch": 1.02, + "learning_rate": 4.5314171661655844e-05, + "loss": 3.8534, + "step": 286208 + }, + { + "epoch": 1.02, + "learning_rate": 4.5305785714145324e-05, + "loss": 3.8572, + "step": 286720 + }, + { + "epoch": 1.02, + "learning_rate": 4.5297399766634804e-05, + "loss": 3.8583, + "step": 287232 + }, + { + "epoch": 1.02, + "learning_rate": 4.5289013819124284e-05, + "loss": 3.8695, + "step": 287744 + }, + { + "epoch": 1.02, + "learning_rate": 4.52806442504175e-05, + "loss": 3.8698, + "step": 288256 + }, + { + "epoch": 1.02, + "learning_rate": 4.527227468171071e-05, + "loss": 3.8594, + "step": 288768 + }, + { + "epoch": 1.02, + "learning_rate": 4.526388873420019e-05, + "loss": 3.8515, + "step": 289280 + }, + { + "epoch": 1.02, + "learning_rate": 4.525550278668967e-05, + "loss": 3.8528, + "step": 289792 + }, + { + "epoch": 1.02, + "learning_rate": 4.524711683917915e-05, + "loss": 3.8587, + "step": 290304 + }, + { + "epoch": 1.02, + "learning_rate": 4.523873089166863e-05, + "loss": 3.8499, + "step": 290816 + }, + { + "epoch": 1.02, + "learning_rate": 4.523034494415811e-05, + "loss": 3.8544, + "step": 291328 + }, + { + "epoch": 1.02, + "learning_rate": 4.522195899664759e-05, + "loss": 3.8528, + "step": 291840 + }, + { + "epoch": 1.02, + "learning_rate": 4.521357304913707e-05, + "loss": 3.8521, + "step": 292352 + }, + { + "epoch": 1.02, + "learning_rate": 4.520520348043028e-05, + "loss": 3.8478, + "step": 292864 + }, + { + "epoch": 1.02, + "learning_rate": 4.519681753291976e-05, + "loss": 3.8487, + "step": 293376 + }, + { + "epoch": 1.02, + "learning_rate": 4.518843158540924e-05, + "loss": 3.8479, + "step": 293888 + }, + { + "epoch": 1.02, + "learning_rate": 4.5180045637898725e-05, + "loss": 3.8523, + "step": 294400 + }, + { + "epoch": 1.02, + "learning_rate": 4.5171676069191934e-05, + "loss": 3.8383, + "step": 294912 + }, + { + "epoch": 1.02, + "learning_rate": 4.5163290121681414e-05, + "loss": 3.8654, + "step": 295424 + }, + { + "epoch": 1.02, + "learning_rate": 4.5154904174170894e-05, + "loss": 3.8632, + "step": 295936 + }, + { + "epoch": 1.02, + "learning_rate": 4.5146518226660373e-05, + "loss": 3.8585, + "step": 296448 + }, + { + "epoch": 1.02, + "learning_rate": 4.513814865795358e-05, + "loss": 3.8364, + "step": 296960 + }, + { + "epoch": 1.02, + "learning_rate": 4.512976271044306e-05, + "loss": 3.8536, + "step": 297472 + }, + { + "epoch": 1.02, + "learning_rate": 4.512137676293254e-05, + "loss": 3.8575, + "step": 297984 + }, + { + "epoch": 1.02, + "learning_rate": 4.511299081542202e-05, + "loss": 3.8537, + "step": 298496 + }, + { + "epoch": 1.02, + "learning_rate": 4.510462124671523e-05, + "loss": 3.8519, + "step": 299008 + }, + { + "epoch": 1.02, + "learning_rate": 4.509623529920471e-05, + "loss": 3.8519, + "step": 299520 + }, + { + "epoch": 1.02, + "learning_rate": 4.508784935169419e-05, + "loss": 3.8501, + "step": 300032 + }, + { + "epoch": 1.02, + "learning_rate": 4.507946340418368e-05, + "loss": 3.8574, + "step": 300544 + }, + { + "epoch": 1.02, + "learning_rate": 4.507109383547689e-05, + "loss": 3.8471, + "step": 301056 + }, + { + "epoch": 1.02, + "learning_rate": 4.506270788796637e-05, + "loss": 3.8504, + "step": 301568 + }, + { + "epoch": 1.02, + "learning_rate": 4.505432194045585e-05, + "loss": 3.8501, + "step": 302080 + }, + { + "epoch": 1.02, + "learning_rate": 4.504593599294533e-05, + "loss": 3.8388, + "step": 302592 + }, + { + "epoch": 1.02, + "learning_rate": 4.5037566424238536e-05, + "loss": 3.8563, + "step": 303104 + }, + { + "epoch": 1.02, + "learning_rate": 4.5029180476728016e-05, + "loss": 3.8523, + "step": 303616 + }, + { + "epoch": 1.02, + "learning_rate": 4.5020794529217496e-05, + "loss": 3.85, + "step": 304128 + }, + { + "epoch": 1.02, + "learning_rate": 4.5012408581706976e-05, + "loss": 3.8396, + "step": 304640 + }, + { + "epoch": 1.02, + "learning_rate": 4.500402263419645e-05, + "loss": 3.8414, + "step": 305152 + }, + { + "epoch": 1.03, + "eval_loss": 3.909769058227539, + "eval_runtime": 307.4618, + "eval_samples_per_second": 1241.101, + "eval_steps_per_second": 38.785, + "step": 305280 + }, + { + "epoch": 0.0, + "learning_rate": 4.499563668668593e-05, + "loss": 3.8395, + "step": 305664 + }, + { + "epoch": 0.0, + "learning_rate": 4.4987250739175416e-05, + "loss": 3.8349, + "step": 306176 + }, + { + "epoch": 0.0, + "learning_rate": 4.4978864791664896e-05, + "loss": 3.8475, + "step": 306688 + }, + { + "epoch": 0.0, + "learning_rate": 4.4970478844154376e-05, + "loss": 3.8428, + "step": 307200 + }, + { + "epoch": 0.0, + "learning_rate": 4.4962092896643856e-05, + "loss": 3.859, + "step": 307712 + }, + { + "epoch": 0.0, + "learning_rate": 4.4953706949133336e-05, + "loss": 3.8336, + "step": 308224 + }, + { + "epoch": 0.0, + "learning_rate": 4.4945321001622816e-05, + "loss": 3.8396, + "step": 308736 + }, + { + "epoch": 0.0, + "learning_rate": 4.4936935054112296e-05, + "loss": 3.8267, + "step": 309248 + }, + { + "epoch": 0.0, + "learning_rate": 4.4928565485405505e-05, + "loss": 3.8468, + "step": 309760 + }, + { + "epoch": 0.0, + "learning_rate": 4.4920179537894985e-05, + "loss": 3.8432, + "step": 310272 + }, + { + "epoch": 0.0, + "learning_rate": 4.4911793590384465e-05, + "loss": 3.8415, + "step": 310784 + }, + { + "epoch": 0.0, + "learning_rate": 4.4903407642873945e-05, + "loss": 3.8414, + "step": 311296 + }, + { + "epoch": 0.0, + "learning_rate": 4.4895038074167154e-05, + "loss": 3.8298, + "step": 311808 + }, + { + "epoch": 0.0, + "learning_rate": 4.4886652126656634e-05, + "loss": 3.8381, + "step": 312320 + }, + { + "epoch": 0.0, + "learning_rate": 4.4878266179146114e-05, + "loss": 3.8258, + "step": 312832 + }, + { + "epoch": 0.0, + "learning_rate": 4.48698802316356e-05, + "loss": 3.8339, + "step": 313344 + }, + { + "epoch": 0.0, + "learning_rate": 4.486151066292881e-05, + "loss": 3.83, + "step": 313856 + }, + { + "epoch": 0.0, + "learning_rate": 4.485312471541829e-05, + "loss": 3.8305, + "step": 314368 + }, + { + "epoch": 0.0, + "learning_rate": 4.484473876790777e-05, + "loss": 3.8343, + "step": 314880 + }, + { + "epoch": 0.0, + "learning_rate": 4.483635282039725e-05, + "loss": 3.851, + "step": 315392 + }, + { + "epoch": 0.0, + "learning_rate": 4.482798325169046e-05, + "loss": 3.8323, + "step": 315904 + }, + { + "epoch": 0.0, + "learning_rate": 4.481959730417994e-05, + "loss": 3.838, + "step": 316416 + }, + { + "epoch": 0.0, + "learning_rate": 4.481121135666942e-05, + "loss": 3.8305, + "step": 316928 + }, + { + "epoch": 0.0, + "learning_rate": 4.48028254091589e-05, + "loss": 3.8404, + "step": 317440 + }, + { + "epoch": 0.0, + "learning_rate": 4.479445584045211e-05, + "loss": 3.8263, + "step": 317952 + }, + { + "epoch": 0.0, + "learning_rate": 4.478606989294159e-05, + "loss": 3.8371, + "step": 318464 + }, + { + "epoch": 0.0, + "learning_rate": 4.477768394543107e-05, + "loss": 3.8295, + "step": 318976 + }, + { + "epoch": 0.0, + "learning_rate": 4.476931437672428e-05, + "loss": 3.8248, + "step": 319488 + }, + { + "epoch": 0.0, + "learning_rate": 4.476092842921376e-05, + "loss": 3.8184, + "step": 320000 + }, + { + "epoch": 0.0, + "learning_rate": 4.475254248170324e-05, + "loss": 3.8242, + "step": 320512 + }, + { + "epoch": 0.01, + "learning_rate": 4.474415653419272e-05, + "loss": 3.8305, + "step": 321024 + }, + { + "epoch": 0.01, + "learning_rate": 4.473578696548593e-05, + "loss": 3.8347, + "step": 321536 + }, + { + "epoch": 0.01, + "learning_rate": 4.472740101797541e-05, + "loss": 3.8355, + "step": 322048 + }, + { + "epoch": 0.01, + "learning_rate": 4.471901507046489e-05, + "loss": 3.8294, + "step": 322560 + }, + { + "epoch": 0.01, + "learning_rate": 4.471062912295437e-05, + "loss": 3.8239, + "step": 323072 + }, + { + "epoch": 0.01, + "learning_rate": 4.470225955424758e-05, + "loss": 3.8382, + "step": 323584 + }, + { + "epoch": 0.01, + "learning_rate": 4.469387360673706e-05, + "loss": 3.825, + "step": 324096 + }, + { + "epoch": 0.01, + "learning_rate": 4.468548765922654e-05, + "loss": 3.8249, + "step": 324608 + }, + { + "epoch": 0.01, + "learning_rate": 4.467710171171602e-05, + "loss": 3.8101, + "step": 325120 + }, + { + "epoch": 0.01, + "learning_rate": 4.466873214300924e-05, + "loss": 3.8257, + "step": 325632 + }, + { + "epoch": 0.01, + "learning_rate": 4.466034619549872e-05, + "loss": 3.8205, + "step": 326144 + }, + { + "epoch": 0.01, + "learning_rate": 4.46519602479882e-05, + "loss": 3.831, + "step": 326656 + }, + { + "epoch": 0.01, + "learning_rate": 4.464357430047768e-05, + "loss": 3.8252, + "step": 327168 + }, + { + "epoch": 0.01, + "learning_rate": 4.4635204731770886e-05, + "loss": 3.8145, + "step": 327680 + }, + { + "epoch": 0.01, + "learning_rate": 4.4626818784260366e-05, + "loss": 3.8298, + "step": 328192 + }, + { + "epoch": 0.01, + "learning_rate": 4.4618432836749846e-05, + "loss": 3.8195, + "step": 328704 + }, + { + "epoch": 0.01, + "learning_rate": 4.4610046889239326e-05, + "loss": 3.8168, + "step": 329216 + }, + { + "epoch": 0.01, + "learning_rate": 4.4601677320532535e-05, + "loss": 3.8102, + "step": 329728 + }, + { + "epoch": 0.01, + "learning_rate": 4.4593291373022015e-05, + "loss": 3.81, + "step": 330240 + }, + { + "epoch": 0.01, + "learning_rate": 4.4584905425511495e-05, + "loss": 3.825, + "step": 330752 + }, + { + "epoch": 0.01, + "learning_rate": 4.4576519478000975e-05, + "loss": 3.8188, + "step": 331264 + }, + { + "epoch": 0.01, + "learning_rate": 4.456814990929419e-05, + "loss": 3.818, + "step": 331776 + }, + { + "epoch": 0.01, + "learning_rate": 4.455976396178367e-05, + "loss": 3.8096, + "step": 332288 + }, + { + "epoch": 0.01, + "learning_rate": 4.455137801427315e-05, + "loss": 3.8194, + "step": 332800 + }, + { + "epoch": 0.01, + "learning_rate": 4.454299206676263e-05, + "loss": 3.8044, + "step": 333312 + }, + { + "epoch": 0.01, + "learning_rate": 4.453462249805584e-05, + "loss": 3.822, + "step": 333824 + }, + { + "epoch": 0.01, + "learning_rate": 4.452623655054532e-05, + "loss": 3.8055, + "step": 334336 + }, + { + "epoch": 0.01, + "learning_rate": 4.45178506030348e-05, + "loss": 3.8193, + "step": 334848 + }, + { + "epoch": 0.01, + "learning_rate": 4.450946465552428e-05, + "loss": 3.8177, + "step": 335360 + }, + { + "epoch": 0.01, + "learning_rate": 4.450109508681749e-05, + "loss": 3.8108, + "step": 335872 + }, + { + "epoch": 0.01, + "learning_rate": 4.449270913930697e-05, + "loss": 3.8061, + "step": 336384 + }, + { + "epoch": 0.01, + "learning_rate": 4.448432319179645e-05, + "loss": 3.817, + "step": 336896 + }, + { + "epoch": 0.01, + "learning_rate": 4.447593724428593e-05, + "loss": 3.8024, + "step": 337408 + }, + { + "epoch": 0.01, + "learning_rate": 4.4467567675579144e-05, + "loss": 3.8109, + "step": 337920 + }, + { + "epoch": 0.01, + "learning_rate": 4.4459181728068624e-05, + "loss": 3.8181, + "step": 338432 + }, + { + "epoch": 0.01, + "learning_rate": 4.4450795780558104e-05, + "loss": 3.8145, + "step": 338944 + }, + { + "epoch": 0.01, + "learning_rate": 4.4442409833047584e-05, + "loss": 3.8041, + "step": 339456 + }, + { + "epoch": 0.01, + "learning_rate": 4.443404026434079e-05, + "loss": 3.8068, + "step": 339968 + }, + { + "epoch": 0.01, + "learning_rate": 4.442565431683027e-05, + "loss": 3.8032, + "step": 340480 + }, + { + "epoch": 0.01, + "learning_rate": 4.441726836931975e-05, + "loss": 3.8069, + "step": 340992 + }, + { + "epoch": 0.01, + "learning_rate": 4.440888242180923e-05, + "loss": 3.8191, + "step": 341504 + }, + { + "epoch": 0.01, + "learning_rate": 4.440051285310244e-05, + "loss": 3.8137, + "step": 342016 + }, + { + "epoch": 0.01, + "learning_rate": 4.439212690559192e-05, + "loss": 3.8248, + "step": 342528 + }, + { + "epoch": 0.01, + "learning_rate": 4.43837409580814e-05, + "loss": 3.8228, + "step": 343040 + }, + { + "epoch": 0.01, + "learning_rate": 4.437535501057088e-05, + "loss": 3.821, + "step": 343552 + }, + { + "epoch": 0.01, + "learning_rate": 4.43669854418641e-05, + "loss": 3.8013, + "step": 344064 + }, + { + "epoch": 0.01, + "learning_rate": 4.435859949435358e-05, + "loss": 3.8114, + "step": 344576 + }, + { + "epoch": 0.01, + "learning_rate": 4.435021354684306e-05, + "loss": 3.8204, + "step": 345088 + }, + { + "epoch": 0.01, + "learning_rate": 4.434184397813627e-05, + "loss": 3.8072, + "step": 345600 + }, + { + "epoch": 0.01, + "learning_rate": 4.433345803062575e-05, + "loss": 3.8088, + "step": 346112 + }, + { + "epoch": 0.01, + "learning_rate": 4.432507208311523e-05, + "loss": 3.8115, + "step": 346624 + }, + { + "epoch": 0.01, + "learning_rate": 4.431668613560471e-05, + "loss": 3.8268, + "step": 347136 + }, + { + "epoch": 0.01, + "learning_rate": 4.430830018809418e-05, + "loss": 3.809, + "step": 347648 + }, + { + "epoch": 0.01, + "learning_rate": 4.429991424058366e-05, + "loss": 3.7949, + "step": 348160 + }, + { + "epoch": 0.01, + "learning_rate": 4.429152829307314e-05, + "loss": 3.8046, + "step": 348672 + }, + { + "epoch": 0.01, + "learning_rate": 4.428314234556262e-05, + "loss": 3.8092, + "step": 349184 + }, + { + "epoch": 0.01, + "learning_rate": 4.4274772776855836e-05, + "loss": 3.8144, + "step": 349696 + }, + { + "epoch": 0.01, + "learning_rate": 4.4266386829345316e-05, + "loss": 3.8139, + "step": 350208 + }, + { + "epoch": 0.01, + "learning_rate": 4.4258000881834796e-05, + "loss": 3.8014, + "step": 350720 + }, + { + "epoch": 0.02, + "learning_rate": 4.4249614934324276e-05, + "loss": 3.8053, + "step": 351232 + }, + { + "epoch": 0.02, + "learning_rate": 4.4241245365617485e-05, + "loss": 3.8018, + "step": 351744 + }, + { + "epoch": 0.02, + "learning_rate": 4.4232859418106965e-05, + "loss": 3.7986, + "step": 352256 + }, + { + "epoch": 0.02, + "learning_rate": 4.4224473470596445e-05, + "loss": 3.805, + "step": 352768 + }, + { + "epoch": 0.02, + "learning_rate": 4.4216087523085925e-05, + "loss": 3.8118, + "step": 353280 + }, + { + "epoch": 0.02, + "learning_rate": 4.4207717954379134e-05, + "loss": 3.8278, + "step": 353792 + }, + { + "epoch": 0.02, + "learning_rate": 4.4199332006868614e-05, + "loss": 3.8089, + "step": 354304 + }, + { + "epoch": 0.02, + "learning_rate": 4.4190946059358094e-05, + "loss": 3.7936, + "step": 354816 + }, + { + "epoch": 0.02, + "learning_rate": 4.4182560111847573e-05, + "loss": 3.8048, + "step": 355328 + }, + { + "epoch": 0.02, + "learning_rate": 4.417419054314079e-05, + "loss": 3.8005, + "step": 355840 + }, + { + "epoch": 0.02, + "learning_rate": 4.416580459563027e-05, + "loss": 3.8146, + "step": 356352 + }, + { + "epoch": 0.02, + "learning_rate": 4.415741864811975e-05, + "loss": 3.807, + "step": 356864 + }, + { + "epoch": 0.02, + "learning_rate": 4.414903270060923e-05, + "loss": 3.8059, + "step": 357376 + }, + { + "epoch": 0.02, + "learning_rate": 4.414066313190244e-05, + "loss": 3.7972, + "step": 357888 + }, + { + "epoch": 0.02, + "learning_rate": 4.413227718439192e-05, + "loss": 3.8102, + "step": 358400 + }, + { + "epoch": 0.02, + "learning_rate": 4.41238912368814e-05, + "loss": 3.7856, + "step": 358912 + }, + { + "epoch": 0.02, + "learning_rate": 4.411550528937088e-05, + "loss": 3.8016, + "step": 359424 + }, + { + "epoch": 0.02, + "learning_rate": 4.410713572066409e-05, + "loss": 3.79, + "step": 359936 + }, + { + "epoch": 0.02, + "learning_rate": 4.409874977315357e-05, + "loss": 3.81, + "step": 360448 + }, + { + "epoch": 0.02, + "learning_rate": 4.409036382564305e-05, + "loss": 3.7944, + "step": 360960 + }, + { + "epoch": 0.02, + "learning_rate": 4.408197787813253e-05, + "loss": 3.7985, + "step": 361472 + }, + { + "epoch": 0.02, + "learning_rate": 4.407360830942574e-05, + "loss": 3.7936, + "step": 361984 + }, + { + "epoch": 0.02, + "learning_rate": 4.406522236191522e-05, + "loss": 3.8004, + "step": 362496 + }, + { + "epoch": 0.02, + "learning_rate": 4.40568364144047e-05, + "loss": 3.8017, + "step": 363008 + }, + { + "epoch": 0.02, + "learning_rate": 4.404845046689418e-05, + "loss": 3.7993, + "step": 363520 + }, + { + "epoch": 0.02, + "learning_rate": 4.404008089818739e-05, + "loss": 3.8116, + "step": 364032 + }, + { + "epoch": 0.02, + "learning_rate": 4.40317113294806e-05, + "loss": 3.8123, + "step": 364544 + }, + { + "epoch": 0.02, + "learning_rate": 4.402332538197008e-05, + "loss": 3.8021, + "step": 365056 + }, + { + "epoch": 0.02, + "learning_rate": 4.401493943445956e-05, + "loss": 3.7955, + "step": 365568 + }, + { + "epoch": 0.02, + "learning_rate": 4.400655348694904e-05, + "loss": 3.7963, + "step": 366080 + }, + { + "epoch": 0.02, + "learning_rate": 4.399818391824225e-05, + "loss": 3.8061, + "step": 366592 + }, + { + "epoch": 0.02, + "learning_rate": 4.398979797073173e-05, + "loss": 3.7874, + "step": 367104 + }, + { + "epoch": 0.02, + "learning_rate": 4.398141202322122e-05, + "loss": 3.8025, + "step": 367616 + }, + { + "epoch": 0.02, + "learning_rate": 4.39730260757107e-05, + "loss": 3.7911, + "step": 368128 + }, + { + "epoch": 0.02, + "learning_rate": 4.396464012820018e-05, + "loss": 3.7969, + "step": 368640 + }, + { + "epoch": 0.02, + "learning_rate": 4.3956254180689657e-05, + "loss": 3.7942, + "step": 369152 + }, + { + "epoch": 0.02, + "learning_rate": 4.3947868233179137e-05, + "loss": 3.7944, + "step": 369664 + }, + { + "epoch": 0.02, + "learning_rate": 4.3939498664472346e-05, + "loss": 3.7882, + "step": 370176 + }, + { + "epoch": 0.02, + "learning_rate": 4.3931112716961826e-05, + "loss": 3.8007, + "step": 370688 + }, + { + "epoch": 0.02, + "learning_rate": 4.3922726769451306e-05, + "loss": 3.786, + "step": 371200 + }, + { + "epoch": 0.02, + "learning_rate": 4.3914340821940786e-05, + "loss": 3.8077, + "step": 371712 + }, + { + "epoch": 0.02, + "learning_rate": 4.3905971253233995e-05, + "loss": 3.8018, + "step": 372224 + }, + { + "epoch": 0.02, + "learning_rate": 4.3897585305723475e-05, + "loss": 3.8092, + "step": 372736 + }, + { + "epoch": 0.02, + "learning_rate": 4.3889199358212955e-05, + "loss": 3.779, + "step": 373248 + }, + { + "epoch": 0.02, + "learning_rate": 4.3880813410702434e-05, + "loss": 3.8012, + "step": 373760 + }, + { + "epoch": 0.02, + "learning_rate": 4.387244384199565e-05, + "loss": 3.8003, + "step": 374272 + }, + { + "epoch": 0.02, + "learning_rate": 4.386405789448513e-05, + "loss": 3.7979, + "step": 374784 + }, + { + "epoch": 0.02, + "learning_rate": 4.385567194697461e-05, + "loss": 3.7961, + "step": 375296 + }, + { + "epoch": 0.02, + "learning_rate": 4.384728599946409e-05, + "loss": 3.7993, + "step": 375808 + }, + { + "epoch": 0.02, + "learning_rate": 4.38389164307573e-05, + "loss": 3.7937, + "step": 376320 + }, + { + "epoch": 0.02, + "learning_rate": 4.383053048324678e-05, + "loss": 3.8051, + "step": 376832 + }, + { + "epoch": 0.02, + "learning_rate": 4.382214453573626e-05, + "loss": 3.7871, + "step": 377344 + }, + { + "epoch": 0.02, + "learning_rate": 4.381377496702947e-05, + "loss": 3.7971, + "step": 377856 + }, + { + "epoch": 0.02, + "learning_rate": 4.380538901951895e-05, + "loss": 3.7951, + "step": 378368 + }, + { + "epoch": 0.02, + "learning_rate": 4.379700307200843e-05, + "loss": 3.786, + "step": 378880 + }, + { + "epoch": 0.02, + "learning_rate": 4.378861712449791e-05, + "loss": 3.7979, + "step": 379392 + }, + { + "epoch": 0.02, + "learning_rate": 4.378023117698739e-05, + "loss": 3.8018, + "step": 379904 + }, + { + "epoch": 0.02, + "learning_rate": 4.3771861608280604e-05, + "loss": 3.7938, + "step": 380416 + }, + { + "epoch": 0.02, + "learning_rate": 4.3763475660770084e-05, + "loss": 3.7841, + "step": 380928 + }, + { + "epoch": 0.02, + "learning_rate": 4.3755089713259564e-05, + "loss": 3.7915, + "step": 381440 + }, + { + "epoch": 0.03, + "eval_loss": 3.884277105331421, + "eval_runtime": 308.3892, + "eval_samples_per_second": 1237.368, + "eval_steps_per_second": 38.669, + "step": 381600 + }, + { + "epoch": 1.0, + "learning_rate": 4.3746703765749044e-05, + "loss": 3.7934, + "step": 381952 + }, + { + "epoch": 1.0, + "learning_rate": 4.3738317818238524e-05, + "loss": 3.7809, + "step": 382464 + }, + { + "epoch": 1.0, + "learning_rate": 4.3729931870728004e-05, + "loss": 3.7909, + "step": 382976 + }, + { + "epoch": 1.0, + "learning_rate": 4.3721545923217484e-05, + "loss": 3.7934, + "step": 383488 + }, + { + "epoch": 1.0, + "learning_rate": 4.371315997570696e-05, + "loss": 3.8025, + "step": 384000 + }, + { + "epoch": 1.0, + "learning_rate": 4.370479040700017e-05, + "loss": 3.7871, + "step": 384512 + }, + { + "epoch": 1.0, + "learning_rate": 4.369640445948965e-05, + "loss": 3.784, + "step": 385024 + }, + { + "epoch": 1.0, + "learning_rate": 4.368801851197913e-05, + "loss": 3.7751, + "step": 385536 + }, + { + "epoch": 1.0, + "learning_rate": 4.3679632564468606e-05, + "loss": 3.7896, + "step": 386048 + }, + { + "epoch": 1.0, + "learning_rate": 4.367126299576182e-05, + "loss": 3.7927, + "step": 386560 + }, + { + "epoch": 1.0, + "learning_rate": 4.36628770482513e-05, + "loss": 3.7875, + "step": 387072 + }, + { + "epoch": 1.0, + "learning_rate": 4.365449110074079e-05, + "loss": 3.7893, + "step": 387584 + }, + { + "epoch": 1.0, + "learning_rate": 4.364610515323026e-05, + "loss": 3.7781, + "step": 388096 + }, + { + "epoch": 1.0, + "learning_rate": 4.363773558452348e-05, + "loss": 3.7866, + "step": 388608 + }, + { + "epoch": 1.0, + "learning_rate": 4.362934963701296e-05, + "loss": 3.7753, + "step": 389120 + }, + { + "epoch": 1.0, + "learning_rate": 4.362096368950243e-05, + "loss": 3.7822, + "step": 389632 + }, + { + "epoch": 1.0, + "learning_rate": 4.361257774199191e-05, + "loss": 3.7743, + "step": 390144 + }, + { + "epoch": 1.0, + "learning_rate": 4.3604208173285126e-05, + "loss": 3.7827, + "step": 390656 + }, + { + "epoch": 1.0, + "learning_rate": 4.3595822225774606e-05, + "loss": 3.7776, + "step": 391168 + }, + { + "epoch": 1.0, + "learning_rate": 4.358743627826408e-05, + "loss": 3.7967, + "step": 391680 + }, + { + "epoch": 1.0, + "learning_rate": 4.357905033075356e-05, + "loss": 3.7826, + "step": 392192 + }, + { + "epoch": 1.0, + "learning_rate": 4.357069714085051e-05, + "loss": 3.791, + "step": 392704 + }, + { + "epoch": 1.0, + "learning_rate": 4.356231119333999e-05, + "loss": 3.7763, + "step": 393216 + }, + { + "epoch": 1.0, + "learning_rate": 4.355392524582947e-05, + "loss": 3.788, + "step": 393728 + }, + { + "epoch": 1.0, + "learning_rate": 4.354553929831895e-05, + "loss": 3.773, + "step": 394240 + }, + { + "epoch": 1.0, + "learning_rate": 4.353716972961216e-05, + "loss": 3.7869, + "step": 394752 + }, + { + "epoch": 1.0, + "learning_rate": 4.352878378210164e-05, + "loss": 3.7815, + "step": 395264 + }, + { + "epoch": 1.0, + "learning_rate": 4.352039783459112e-05, + "loss": 3.7691, + "step": 395776 + }, + { + "epoch": 1.0, + "learning_rate": 4.35120118870806e-05, + "loss": 3.7652, + "step": 396288 + }, + { + "epoch": 1.0, + "learning_rate": 4.350362593957008e-05, + "loss": 3.7726, + "step": 396800 + }, + { + "epoch": 1.01, + "learning_rate": 4.349523999205955e-05, + "loss": 3.7805, + "step": 397312 + }, + { + "epoch": 1.01, + "learning_rate": 4.348685404454903e-05, + "loss": 3.7823, + "step": 397824 + }, + { + "epoch": 1.01, + "learning_rate": 4.347846809703851e-05, + "loss": 3.7852, + "step": 398336 + }, + { + "epoch": 1.01, + "learning_rate": 4.347009852833173e-05, + "loss": 3.7844, + "step": 398848 + }, + { + "epoch": 1.01, + "learning_rate": 4.346171258082121e-05, + "loss": 3.7743, + "step": 399360 + }, + { + "epoch": 1.01, + "learning_rate": 4.345332663331069e-05, + "loss": 3.7848, + "step": 399872 + }, + { + "epoch": 1.01, + "learning_rate": 4.3444957064603905e-05, + "loss": 3.776, + "step": 400384 + }, + { + "epoch": 1.01, + "learning_rate": 4.343657111709338e-05, + "loss": 3.7729, + "step": 400896 + }, + { + "epoch": 1.01, + "learning_rate": 4.342818516958286e-05, + "loss": 3.7594, + "step": 401408 + }, + { + "epoch": 1.01, + "learning_rate": 4.341979922207234e-05, + "loss": 3.7764, + "step": 401920 + }, + { + "epoch": 1.01, + "learning_rate": 4.3411429653365554e-05, + "loss": 3.7706, + "step": 402432 + }, + { + "epoch": 1.01, + "learning_rate": 4.340304370585503e-05, + "loss": 3.7793, + "step": 402944 + }, + { + "epoch": 1.01, + "learning_rate": 4.339465775834451e-05, + "loss": 3.773, + "step": 403456 + }, + { + "epoch": 1.01, + "learning_rate": 4.338627181083399e-05, + "loss": 3.7668, + "step": 403968 + }, + { + "epoch": 1.01, + "learning_rate": 4.337788586332347e-05, + "loss": 3.7804, + "step": 404480 + }, + { + "epoch": 1.01, + "learning_rate": 4.336951629461668e-05, + "loss": 3.7681, + "step": 404992 + }, + { + "epoch": 1.01, + "learning_rate": 4.336113034710616e-05, + "loss": 3.7695, + "step": 405504 + }, + { + "epoch": 1.01, + "learning_rate": 4.335274439959564e-05, + "loss": 3.7622, + "step": 406016 + }, + { + "epoch": 1.01, + "learning_rate": 4.334435845208512e-05, + "loss": 3.7597, + "step": 406528 + }, + { + "epoch": 1.01, + "learning_rate": 4.33359725045746e-05, + "loss": 3.7738, + "step": 407040 + }, + { + "epoch": 1.01, + "learning_rate": 4.332758655706408e-05, + "loss": 3.7713, + "step": 407552 + }, + { + "epoch": 1.01, + "learning_rate": 4.331921698835729e-05, + "loss": 3.7685, + "step": 408064 + }, + { + "epoch": 1.01, + "learning_rate": 4.331083104084677e-05, + "loss": 3.7617, + "step": 408576 + }, + { + "epoch": 1.01, + "learning_rate": 4.330244509333625e-05, + "loss": 3.7713, + "step": 409088 + }, + { + "epoch": 1.01, + "learning_rate": 4.329405914582573e-05, + "loss": 3.7514, + "step": 409600 + }, + { + "epoch": 1.01, + "learning_rate": 4.328568957711894e-05, + "loss": 3.7745, + "step": 410112 + }, + { + "epoch": 1.01, + "learning_rate": 4.327730362960842e-05, + "loss": 3.759, + "step": 410624 + }, + { + "epoch": 1.01, + "learning_rate": 4.32689176820979e-05, + "loss": 3.7694, + "step": 411136 + }, + { + "epoch": 1.01, + "learning_rate": 4.326053173458739e-05, + "loss": 3.7679, + "step": 411648 + }, + { + "epoch": 1.01, + "learning_rate": 4.325214578707687e-05, + "loss": 3.7645, + "step": 412160 + }, + { + "epoch": 1.01, + "learning_rate": 4.324375983956635e-05, + "loss": 3.7584, + "step": 412672 + }, + { + "epoch": 1.01, + "learning_rate": 4.323537389205583e-05, + "loss": 3.7672, + "step": 413184 + }, + { + "epoch": 1.01, + "learning_rate": 4.322698794454531e-05, + "loss": 3.7599, + "step": 413696 + }, + { + "epoch": 1.01, + "learning_rate": 4.3218618375838516e-05, + "loss": 3.7587, + "step": 414208 + }, + { + "epoch": 1.01, + "learning_rate": 4.3210232428327996e-05, + "loss": 3.7699, + "step": 414720 + }, + { + "epoch": 1.01, + "learning_rate": 4.3201846480817476e-05, + "loss": 3.7657, + "step": 415232 + }, + { + "epoch": 1.01, + "learning_rate": 4.3193460533306956e-05, + "loss": 3.7535, + "step": 415744 + }, + { + "epoch": 1.01, + "learning_rate": 4.3185074585796436e-05, + "loss": 3.7646, + "step": 416256 + }, + { + "epoch": 1.01, + "learning_rate": 4.3176688638285916e-05, + "loss": 3.7524, + "step": 416768 + }, + { + "epoch": 1.01, + "learning_rate": 4.316830269077539e-05, + "loss": 3.758, + "step": 417280 + }, + { + "epoch": 1.01, + "learning_rate": 4.315991674326487e-05, + "loss": 3.7734, + "step": 417792 + }, + { + "epoch": 1.01, + "learning_rate": 4.3151547174558085e-05, + "loss": 3.7688, + "step": 418304 + }, + { + "epoch": 1.01, + "learning_rate": 4.31431776058513e-05, + "loss": 3.7739, + "step": 418816 + }, + { + "epoch": 1.01, + "learning_rate": 4.313479165834078e-05, + "loss": 3.7706, + "step": 419328 + }, + { + "epoch": 1.01, + "learning_rate": 4.312640571083026e-05, + "loss": 3.7787, + "step": 419840 + }, + { + "epoch": 1.01, + "learning_rate": 4.311801976331974e-05, + "loss": 3.7576, + "step": 420352 + }, + { + "epoch": 1.01, + "learning_rate": 4.3109633815809214e-05, + "loss": 3.7618, + "step": 420864 + }, + { + "epoch": 1.01, + "learning_rate": 4.3101247868298694e-05, + "loss": 3.7733, + "step": 421376 + }, + { + "epoch": 1.01, + "learning_rate": 4.3092861920788174e-05, + "loss": 3.7581, + "step": 421888 + }, + { + "epoch": 1.01, + "learning_rate": 4.308449235208139e-05, + "loss": 3.7649, + "step": 422400 + }, + { + "epoch": 1.01, + "learning_rate": 4.307610640457086e-05, + "loss": 3.7684, + "step": 422912 + }, + { + "epoch": 1.01, + "learning_rate": 4.306772045706034e-05, + "loss": 3.7719, + "step": 423424 + }, + { + "epoch": 1.01, + "learning_rate": 4.305933450954982e-05, + "loss": 3.7622, + "step": 423936 + }, + { + "epoch": 1.01, + "learning_rate": 4.305096494084304e-05, + "loss": 3.7514, + "step": 424448 + }, + { + "epoch": 1.01, + "learning_rate": 4.304257899333252e-05, + "loss": 3.7581, + "step": 424960 + }, + { + "epoch": 1.01, + "learning_rate": 4.3034193045822e-05, + "loss": 3.7619, + "step": 425472 + }, + { + "epoch": 1.01, + "learning_rate": 4.302580709831148e-05, + "loss": 3.7681, + "step": 425984 + }, + { + "epoch": 1.01, + "learning_rate": 4.301742115080096e-05, + "loss": 3.7651, + "step": 426496 + }, + { + "epoch": 1.01, + "learning_rate": 4.300903520329044e-05, + "loss": 3.758, + "step": 427008 + }, + { + "epoch": 1.02, + "learning_rate": 4.300064925577992e-05, + "loss": 3.7617, + "step": 427520 + }, + { + "epoch": 1.02, + "learning_rate": 4.299227968707313e-05, + "loss": 3.7538, + "step": 428032 + }, + { + "epoch": 1.02, + "learning_rate": 4.298389373956261e-05, + "loss": 3.7505, + "step": 428544 + }, + { + "epoch": 1.02, + "learning_rate": 4.2975524170855817e-05, + "loss": 3.7559, + "step": 429056 + }, + { + "epoch": 1.02, + "learning_rate": 4.2967138223345296e-05, + "loss": 3.7663, + "step": 429568 + }, + { + "epoch": 1.02, + "learning_rate": 4.2958752275834776e-05, + "loss": 3.7809, + "step": 430080 + }, + { + "epoch": 1.02, + "learning_rate": 4.2950366328324256e-05, + "loss": 3.7657, + "step": 430592 + }, + { + "epoch": 1.02, + "learning_rate": 4.294198038081374e-05, + "loss": 3.7454, + "step": 431104 + }, + { + "epoch": 1.02, + "learning_rate": 4.293359443330322e-05, + "loss": 3.7622, + "step": 431616 + }, + { + "epoch": 1.02, + "learning_rate": 4.29252084857927e-05, + "loss": 3.7567, + "step": 432128 + }, + { + "epoch": 1.02, + "learning_rate": 4.291682253828218e-05, + "loss": 3.7672, + "step": 432640 + }, + { + "epoch": 1.02, + "learning_rate": 4.290845296957539e-05, + "loss": 3.7574, + "step": 433152 + }, + { + "epoch": 1.02, + "learning_rate": 4.290006702206487e-05, + "loss": 3.7618, + "step": 433664 + }, + { + "epoch": 1.02, + "learning_rate": 4.289169745335808e-05, + "loss": 3.7554, + "step": 434176 + }, + { + "epoch": 1.02, + "learning_rate": 4.288331150584756e-05, + "loss": 3.7588, + "step": 434688 + }, + { + "epoch": 1.02, + "learning_rate": 4.287492555833704e-05, + "loss": 3.7482, + "step": 435200 + }, + { + "epoch": 1.02, + "learning_rate": 4.286653961082652e-05, + "loss": 3.7545, + "step": 435712 + }, + { + "epoch": 1.02, + "learning_rate": 4.2858153663316e-05, + "loss": 3.7443, + "step": 436224 + }, + { + "epoch": 1.02, + "learning_rate": 4.284976771580548e-05, + "loss": 3.7676, + "step": 436736 + }, + { + "epoch": 1.02, + "learning_rate": 4.284138176829496e-05, + "loss": 3.7488, + "step": 437248 + }, + { + "epoch": 1.02, + "learning_rate": 4.283299582078444e-05, + "loss": 3.7523, + "step": 437760 + }, + { + "epoch": 1.02, + "learning_rate": 4.282462625207766e-05, + "loss": 3.7449, + "step": 438272 + }, + { + "epoch": 1.02, + "learning_rate": 4.2816256683370866e-05, + "loss": 3.7584, + "step": 438784 + }, + { + "epoch": 1.02, + "learning_rate": 4.2807870735860346e-05, + "loss": 3.7557, + "step": 439296 + }, + { + "epoch": 1.02, + "learning_rate": 4.2799484788349826e-05, + "loss": 3.7536, + "step": 439808 + }, + { + "epoch": 1.02, + "learning_rate": 4.2791098840839306e-05, + "loss": 3.7661, + "step": 440320 + }, + { + "epoch": 1.02, + "learning_rate": 4.2782712893328786e-05, + "loss": 3.7679, + "step": 440832 + }, + { + "epoch": 1.02, + "learning_rate": 4.2774343324621995e-05, + "loss": 3.7587, + "step": 441344 + }, + { + "epoch": 1.02, + "learning_rate": 4.2765957377111475e-05, + "loss": 3.7537, + "step": 441856 + }, + { + "epoch": 1.02, + "learning_rate": 4.2757571429600955e-05, + "loss": 3.7474, + "step": 442368 + }, + { + "epoch": 1.02, + "learning_rate": 4.2749185482090435e-05, + "loss": 3.7611, + "step": 442880 + }, + { + "epoch": 1.02, + "learning_rate": 4.274081591338365e-05, + "loss": 3.7443, + "step": 443392 + }, + { + "epoch": 1.02, + "learning_rate": 4.273242996587313e-05, + "loss": 3.757, + "step": 443904 + }, + { + "epoch": 1.02, + "learning_rate": 4.272404401836261e-05, + "loss": 3.7444, + "step": 444416 + }, + { + "epoch": 1.02, + "learning_rate": 4.271565807085209e-05, + "loss": 3.7564, + "step": 444928 + }, + { + "epoch": 1.02, + "learning_rate": 4.270727212334157e-05, + "loss": 3.7434, + "step": 445440 + }, + { + "epoch": 1.02, + "learning_rate": 4.269888617583105e-05, + "loss": 3.7513, + "step": 445952 + }, + { + "epoch": 1.02, + "learning_rate": 4.269051660712426e-05, + "loss": 3.7496, + "step": 446464 + }, + { + "epoch": 1.02, + "learning_rate": 4.268213065961374e-05, + "loss": 3.7495, + "step": 446976 + }, + { + "epoch": 1.02, + "learning_rate": 4.267374471210322e-05, + "loss": 3.7454, + "step": 447488 + }, + { + "epoch": 1.02, + "learning_rate": 4.26653587645927e-05, + "loss": 3.7619, + "step": 448000 + }, + { + "epoch": 1.02, + "learning_rate": 4.265697281708217e-05, + "loss": 3.7604, + "step": 448512 + }, + { + "epoch": 1.02, + "learning_rate": 4.264858686957165e-05, + "loss": 3.7619, + "step": 449024 + }, + { + "epoch": 1.02, + "learning_rate": 4.264021730086487e-05, + "loss": 3.7351, + "step": 449536 + }, + { + "epoch": 1.02, + "learning_rate": 4.263183135335435e-05, + "loss": 3.7577, + "step": 450048 + }, + { + "epoch": 1.02, + "learning_rate": 4.262344540584383e-05, + "loss": 3.756, + "step": 450560 + }, + { + "epoch": 1.02, + "learning_rate": 4.261505945833331e-05, + "loss": 3.7578, + "step": 451072 + }, + { + "epoch": 1.02, + "learning_rate": 4.260667351082279e-05, + "loss": 3.7501, + "step": 451584 + }, + { + "epoch": 1.02, + "learning_rate": 4.259828756331227e-05, + "loss": 3.7565, + "step": 452096 + }, + { + "epoch": 1.02, + "learning_rate": 4.258991799460548e-05, + "loss": 3.7519, + "step": 452608 + }, + { + "epoch": 1.02, + "learning_rate": 4.258153204709496e-05, + "loss": 3.763, + "step": 453120 + }, + { + "epoch": 1.02, + "learning_rate": 4.257314609958444e-05, + "loss": 3.7418, + "step": 453632 + }, + { + "epoch": 1.02, + "learning_rate": 4.256476015207392e-05, + "loss": 3.7574, + "step": 454144 + }, + { + "epoch": 1.02, + "learning_rate": 4.2556390583367126e-05, + "loss": 3.7487, + "step": 454656 + }, + { + "epoch": 1.02, + "learning_rate": 4.2548004635856606e-05, + "loss": 3.7465, + "step": 455168 + }, + { + "epoch": 1.02, + "learning_rate": 4.2539618688346086e-05, + "loss": 3.7539, + "step": 455680 + }, + { + "epoch": 1.02, + "learning_rate": 4.253123274083557e-05, + "loss": 3.7533, + "step": 456192 + }, + { + "epoch": 1.02, + "learning_rate": 4.252286317212878e-05, + "loss": 3.7571, + "step": 456704 + }, + { + "epoch": 1.02, + "learning_rate": 4.251447722461826e-05, + "loss": 3.7365, + "step": 457216 + }, + { + "epoch": 1.02, + "learning_rate": 4.250609127710774e-05, + "loss": 3.7489, + "step": 457728 + }, + { + "epoch": 1.03, + "eval_loss": 3.868356943130493, + "eval_runtime": 304.7992, + "eval_samples_per_second": 1251.942, + "eval_steps_per_second": 39.124, + "step": 457920 + }, + { + "epoch": 0.0, + "learning_rate": 4.249770532959722e-05, + "loss": 3.7443, + "step": 458240 + }, + { + "epoch": 0.0, + "learning_rate": 4.24893193820867e-05, + "loss": 3.7377, + "step": 458752 + }, + { + "epoch": 0.0, + "learning_rate": 4.248093343457618e-05, + "loss": 3.7491, + "step": 459264 + }, + { + "epoch": 0.0, + "learning_rate": 4.247254748706566e-05, + "loss": 3.7522, + "step": 459776 + }, + { + "epoch": 0.0, + "learning_rate": 4.246417791835887e-05, + "loss": 3.7612, + "step": 460288 + }, + { + "epoch": 0.0, + "learning_rate": 4.245579197084835e-05, + "loss": 3.7411, + "step": 460800 + }, + { + "epoch": 0.0, + "learning_rate": 4.244740602333783e-05, + "loss": 3.7368, + "step": 461312 + }, + { + "epoch": 0.0, + "learning_rate": 4.243902007582731e-05, + "loss": 3.7381, + "step": 461824 + }, + { + "epoch": 0.0, + "learning_rate": 4.243065050712052e-05, + "loss": 3.741, + "step": 462336 + }, + { + "epoch": 0.0, + "learning_rate": 4.2422264559610006e-05, + "loss": 3.7515, + "step": 462848 + }, + { + "epoch": 0.0, + "learning_rate": 4.2413878612099486e-05, + "loss": 3.7455, + "step": 463360 + }, + { + "epoch": 0.0, + "learning_rate": 4.2405492664588966e-05, + "loss": 3.7472, + "step": 463872 + }, + { + "epoch": 0.0, + "learning_rate": 4.2397106717078446e-05, + "loss": 3.7398, + "step": 464384 + }, + { + "epoch": 0.0, + "learning_rate": 4.2388737148371655e-05, + "loss": 3.7397, + "step": 464896 + }, + { + "epoch": 0.0, + "learning_rate": 4.2380351200861135e-05, + "loss": 3.7363, + "step": 465408 + }, + { + "epoch": 0.0, + "learning_rate": 4.2371965253350615e-05, + "loss": 3.7401, + "step": 465920 + }, + { + "epoch": 0.0, + "learning_rate": 4.2363579305840095e-05, + "loss": 3.7327, + "step": 466432 + }, + { + "epoch": 0.0, + "learning_rate": 4.2355209737133304e-05, + "loss": 3.7374, + "step": 466944 + }, + { + "epoch": 0.0, + "learning_rate": 4.2346823789622784e-05, + "loss": 3.7382, + "step": 467456 + }, + { + "epoch": 0.0, + "learning_rate": 4.2338437842112264e-05, + "loss": 3.7542, + "step": 467968 + }, + { + "epoch": 0.0, + "learning_rate": 4.2330051894601744e-05, + "loss": 3.7419, + "step": 468480 + }, + { + "epoch": 0.0, + "learning_rate": 4.232168232589496e-05, + "loss": 3.7497, + "step": 468992 + }, + { + "epoch": 0.0, + "learning_rate": 4.231329637838444e-05, + "loss": 3.7341, + "step": 469504 + }, + { + "epoch": 0.0, + "learning_rate": 4.230491043087392e-05, + "loss": 3.7469, + "step": 470016 + }, + { + "epoch": 0.0, + "learning_rate": 4.22965244833634e-05, + "loss": 3.7317, + "step": 470528 + }, + { + "epoch": 0.0, + "learning_rate": 4.228815491465661e-05, + "loss": 3.747, + "step": 471040 + }, + { + "epoch": 0.0, + "learning_rate": 4.227976896714609e-05, + "loss": 3.7372, + "step": 471552 + }, + { + "epoch": 0.0, + "learning_rate": 4.227138301963557e-05, + "loss": 3.7277, + "step": 472064 + }, + { + "epoch": 0.0, + "learning_rate": 4.226299707212505e-05, + "loss": 3.729, + "step": 472576 + }, + { + "epoch": 0.0, + "learning_rate": 4.225462750341826e-05, + "loss": 3.7317, + "step": 473088 + }, + { + "epoch": 0.01, + "learning_rate": 4.224624155590774e-05, + "loss": 3.7391, + "step": 473600 + }, + { + "epoch": 0.01, + "learning_rate": 4.223785560839722e-05, + "loss": 3.7406, + "step": 474112 + }, + { + "epoch": 0.01, + "learning_rate": 4.22294696608867e-05, + "loss": 3.7437, + "step": 474624 + }, + { + "epoch": 0.01, + "learning_rate": 4.222108371337618e-05, + "loss": 3.7478, + "step": 475136 + }, + { + "epoch": 0.01, + "learning_rate": 4.2212714144669394e-05, + "loss": 3.7283, + "step": 475648 + }, + { + "epoch": 0.01, + "learning_rate": 4.2204328197158874e-05, + "loss": 3.747, + "step": 476160 + }, + { + "epoch": 0.01, + "learning_rate": 4.2195942249648353e-05, + "loss": 3.7392, + "step": 476672 + }, + { + "epoch": 0.01, + "learning_rate": 4.2187556302137833e-05, + "loss": 3.7279, + "step": 477184 + }, + { + "epoch": 0.01, + "learning_rate": 4.217917035462731e-05, + "loss": 3.7219, + "step": 477696 + }, + { + "epoch": 0.01, + "learning_rate": 4.217080078592052e-05, + "loss": 3.7311, + "step": 478208 + }, + { + "epoch": 0.01, + "learning_rate": 4.216241483841e-05, + "loss": 3.7344, + "step": 478720 + }, + { + "epoch": 0.01, + "learning_rate": 4.2154028890899476e-05, + "loss": 3.7386, + "step": 479232 + }, + { + "epoch": 0.01, + "learning_rate": 4.2145642943388956e-05, + "loss": 3.7319, + "step": 479744 + }, + { + "epoch": 0.01, + "learning_rate": 4.213727337468217e-05, + "loss": 3.7265, + "step": 480256 + }, + { + "epoch": 0.01, + "learning_rate": 4.212888742717165e-05, + "loss": 3.744, + "step": 480768 + }, + { + "epoch": 0.01, + "learning_rate": 4.212050147966113e-05, + "loss": 3.7306, + "step": 481280 + }, + { + "epoch": 0.01, + "learning_rate": 4.211211553215061e-05, + "loss": 3.7287, + "step": 481792 + }, + { + "epoch": 0.01, + "learning_rate": 4.210374596344383e-05, + "loss": 3.7208, + "step": 482304 + }, + { + "epoch": 0.01, + "learning_rate": 4.209536001593331e-05, + "loss": 3.7186, + "step": 482816 + }, + { + "epoch": 0.01, + "learning_rate": 4.208697406842278e-05, + "loss": 3.7358, + "step": 483328 + }, + { + "epoch": 0.01, + "learning_rate": 4.207858812091226e-05, + "loss": 3.7333, + "step": 483840 + }, + { + "epoch": 0.01, + "learning_rate": 4.2070218552205476e-05, + "loss": 3.7276, + "step": 484352 + }, + { + "epoch": 0.01, + "learning_rate": 4.206183260469495e-05, + "loss": 3.7202, + "step": 484864 + }, + { + "epoch": 0.01, + "learning_rate": 4.205344665718443e-05, + "loss": 3.7339, + "step": 485376 + }, + { + "epoch": 0.01, + "learning_rate": 4.204506070967391e-05, + "loss": 3.7096, + "step": 485888 + }, + { + "epoch": 0.01, + "learning_rate": 4.2036691140967125e-05, + "loss": 3.7363, + "step": 486400 + }, + { + "epoch": 0.01, + "learning_rate": 4.2028305193456605e-05, + "loss": 3.7192, + "step": 486912 + }, + { + "epoch": 0.01, + "learning_rate": 4.2019919245946085e-05, + "loss": 3.7232, + "step": 487424 + }, + { + "epoch": 0.01, + "learning_rate": 4.2011533298435565e-05, + "loss": 3.7328, + "step": 487936 + }, + { + "epoch": 0.01, + "learning_rate": 4.200316372972878e-05, + "loss": 3.7229, + "step": 488448 + }, + { + "epoch": 0.01, + "learning_rate": 4.1994777782218254e-05, + "loss": 3.719, + "step": 488960 + }, + { + "epoch": 0.01, + "learning_rate": 4.1986391834707734e-05, + "loss": 3.7336, + "step": 489472 + }, + { + "epoch": 0.01, + "learning_rate": 4.1978005887197214e-05, + "loss": 3.7181, + "step": 489984 + }, + { + "epoch": 0.01, + "learning_rate": 4.1969619939686694e-05, + "loss": 3.7212, + "step": 490496 + }, + { + "epoch": 0.01, + "learning_rate": 4.19612503709799e-05, + "loss": 3.7293, + "step": 491008 + }, + { + "epoch": 0.01, + "learning_rate": 4.195286442346938e-05, + "loss": 3.7291, + "step": 491520 + }, + { + "epoch": 0.01, + "learning_rate": 4.194447847595886e-05, + "loss": 3.7157, + "step": 492032 + }, + { + "epoch": 0.01, + "learning_rate": 4.193609252844834e-05, + "loss": 3.7228, + "step": 492544 + }, + { + "epoch": 0.01, + "learning_rate": 4.192772295974156e-05, + "loss": 3.7117, + "step": 493056 + }, + { + "epoch": 0.01, + "learning_rate": 4.191933701223104e-05, + "loss": 3.7176, + "step": 493568 + }, + { + "epoch": 0.01, + "learning_rate": 4.191095106472052e-05, + "loss": 3.7313, + "step": 494080 + }, + { + "epoch": 0.01, + "learning_rate": 4.190256511721e-05, + "loss": 3.7277, + "step": 494592 + }, + { + "epoch": 0.01, + "learning_rate": 4.189419554850321e-05, + "loss": 3.7361, + "step": 495104 + }, + { + "epoch": 0.01, + "learning_rate": 4.188580960099269e-05, + "loss": 3.7285, + "step": 495616 + }, + { + "epoch": 0.01, + "learning_rate": 4.187742365348217e-05, + "loss": 3.7432, + "step": 496128 + }, + { + "epoch": 0.01, + "learning_rate": 4.186903770597165e-05, + "loss": 3.7167, + "step": 496640 + }, + { + "epoch": 0.01, + "learning_rate": 4.186065175846113e-05, + "loss": 3.7278, + "step": 497152 + }, + { + "epoch": 0.01, + "learning_rate": 4.185228218975434e-05, + "loss": 3.7331, + "step": 497664 + }, + { + "epoch": 0.01, + "learning_rate": 4.1843896242243817e-05, + "loss": 3.7174, + "step": 498176 + }, + { + "epoch": 0.01, + "learning_rate": 4.1835510294733297e-05, + "loss": 3.7266, + "step": 498688 + }, + { + "epoch": 0.01, + "learning_rate": 4.1827124347222776e-05, + "loss": 3.7289, + "step": 499200 + }, + { + "epoch": 0.01, + "learning_rate": 4.181875477851599e-05, + "loss": 3.7349, + "step": 499712 + }, + { + "epoch": 0.01, + "learning_rate": 4.181036883100547e-05, + "loss": 3.7235, + "step": 500224 + }, + { + "epoch": 0.01, + "learning_rate": 4.180198288349495e-05, + "loss": 3.7149, + "step": 500736 + }, + { + "epoch": 0.01, + "learning_rate": 4.179359693598443e-05, + "loss": 3.7157, + "step": 501248 + }, + { + "epoch": 0.01, + "learning_rate": 4.178522736727764e-05, + "loss": 3.723, + "step": 501760 + }, + { + "epoch": 0.01, + "learning_rate": 4.177684141976712e-05, + "loss": 3.7305, + "step": 502272 + }, + { + "epoch": 0.01, + "learning_rate": 4.17684554722566e-05, + "loss": 3.7267, + "step": 502784 + }, + { + "epoch": 0.01, + "learning_rate": 4.176006952474608e-05, + "loss": 3.7247, + "step": 503296 + }, + { + "epoch": 0.02, + "learning_rate": 4.175168357723556e-05, + "loss": 3.715, + "step": 503808 + }, + { + "epoch": 0.02, + "learning_rate": 4.174329762972504e-05, + "loss": 3.7188, + "step": 504320 + }, + { + "epoch": 0.02, + "learning_rate": 4.173492806101825e-05, + "loss": 3.7157, + "step": 504832 + }, + { + "epoch": 0.02, + "learning_rate": 4.172654211350773e-05, + "loss": 3.7197, + "step": 505344 + }, + { + "epoch": 0.02, + "learning_rate": 4.171815616599721e-05, + "loss": 3.7306, + "step": 505856 + }, + { + "epoch": 0.02, + "learning_rate": 4.170977021848669e-05, + "loss": 3.74, + "step": 506368 + }, + { + "epoch": 0.02, + "learning_rate": 4.1701400649779906e-05, + "loss": 3.7291, + "step": 506880 + }, + { + "epoch": 0.02, + "learning_rate": 4.1693014702269386e-05, + "loss": 3.7119, + "step": 507392 + }, + { + "epoch": 0.02, + "learning_rate": 4.1684628754758866e-05, + "loss": 3.7211, + "step": 507904 + }, + { + "epoch": 0.02, + "learning_rate": 4.1676242807248346e-05, + "loss": 3.7188, + "step": 508416 + }, + { + "epoch": 0.02, + "learning_rate": 4.1667856859737826e-05, + "loss": 3.7281, + "step": 508928 + }, + { + "epoch": 0.02, + "learning_rate": 4.1659487291031035e-05, + "loss": 3.7193, + "step": 509440 + }, + { + "epoch": 0.02, + "learning_rate": 4.1651101343520515e-05, + "loss": 3.7272, + "step": 509952 + }, + { + "epoch": 0.02, + "learning_rate": 4.1642715396009995e-05, + "loss": 3.7195, + "step": 510464 + }, + { + "epoch": 0.02, + "learning_rate": 4.1634329448499475e-05, + "loss": 3.7169, + "step": 510976 + }, + { + "epoch": 0.02, + "learning_rate": 4.1625959879792684e-05, + "loss": 3.7137, + "step": 511488 + }, + { + "epoch": 0.02, + "learning_rate": 4.1617573932282164e-05, + "loss": 3.7162, + "step": 512000 + }, + { + "epoch": 0.02, + "learning_rate": 4.1609187984771644e-05, + "loss": 3.7074, + "step": 512512 + }, + { + "epoch": 0.02, + "learning_rate": 4.160080203726113e-05, + "loss": 3.7286, + "step": 513024 + }, + { + "epoch": 0.02, + "learning_rate": 4.159241608975061e-05, + "loss": 3.7132, + "step": 513536 + }, + { + "epoch": 0.02, + "learning_rate": 4.158404652104382e-05, + "loss": 3.7137, + "step": 514048 + }, + { + "epoch": 0.02, + "learning_rate": 4.15756605735333e-05, + "loss": 3.7119, + "step": 514560 + }, + { + "epoch": 0.02, + "learning_rate": 4.156727462602278e-05, + "loss": 3.7167, + "step": 515072 + }, + { + "epoch": 0.02, + "learning_rate": 4.155888867851226e-05, + "loss": 3.7228, + "step": 515584 + }, + { + "epoch": 0.02, + "learning_rate": 4.155051910980547e-05, + "loss": 3.7158, + "step": 516096 + }, + { + "epoch": 0.02, + "learning_rate": 4.154213316229495e-05, + "loss": 3.7316, + "step": 516608 + }, + { + "epoch": 0.02, + "learning_rate": 4.153374721478443e-05, + "loss": 3.7272, + "step": 517120 + }, + { + "epoch": 0.02, + "learning_rate": 4.152536126727391e-05, + "loss": 3.7243, + "step": 517632 + }, + { + "epoch": 0.02, + "learning_rate": 4.151699169856712e-05, + "loss": 3.7198, + "step": 518144 + }, + { + "epoch": 0.02, + "learning_rate": 4.15086057510566e-05, + "loss": 3.7067, + "step": 518656 + }, + { + "epoch": 0.02, + "learning_rate": 4.1500219803546084e-05, + "loss": 3.7294, + "step": 519168 + }, + { + "epoch": 0.02, + "learning_rate": 4.149185023483929e-05, + "loss": 3.714, + "step": 519680 + }, + { + "epoch": 0.02, + "learning_rate": 4.148346428732877e-05, + "loss": 3.7146, + "step": 520192 + }, + { + "epoch": 0.02, + "learning_rate": 4.147507833981825e-05, + "loss": 3.7084, + "step": 520704 + }, + { + "epoch": 0.02, + "learning_rate": 4.146669239230773e-05, + "loss": 3.718, + "step": 521216 + }, + { + "epoch": 0.02, + "learning_rate": 4.145832282360094e-05, + "loss": 3.7088, + "step": 521728 + }, + { + "epoch": 0.02, + "learning_rate": 4.144993687609042e-05, + "loss": 3.7145, + "step": 522240 + }, + { + "epoch": 0.02, + "learning_rate": 4.14415509285799e-05, + "loss": 3.7114, + "step": 522752 + }, + { + "epoch": 0.02, + "learning_rate": 4.143316498106938e-05, + "loss": 3.7171, + "step": 523264 + }, + { + "epoch": 0.02, + "learning_rate": 4.1424779033558855e-05, + "loss": 3.7075, + "step": 523776 + }, + { + "epoch": 0.02, + "learning_rate": 4.141640946485207e-05, + "loss": 3.7262, + "step": 524288 + }, + { + "epoch": 0.02, + "learning_rate": 4.140802351734155e-05, + "loss": 3.7208, + "step": 524800 + }, + { + "epoch": 0.02, + "learning_rate": 4.139963756983103e-05, + "loss": 3.7265, + "step": 525312 + }, + { + "epoch": 0.02, + "learning_rate": 4.139125162232051e-05, + "loss": 3.702, + "step": 525824 + }, + { + "epoch": 0.02, + "learning_rate": 4.138288205361373e-05, + "loss": 3.7221, + "step": 526336 + }, + { + "epoch": 0.02, + "learning_rate": 4.137449610610321e-05, + "loss": 3.7185, + "step": 526848 + }, + { + "epoch": 0.02, + "learning_rate": 4.136611015859268e-05, + "loss": 3.7195, + "step": 527360 + }, + { + "epoch": 0.02, + "learning_rate": 4.135772421108216e-05, + "loss": 3.7166, + "step": 527872 + }, + { + "epoch": 0.02, + "learning_rate": 4.134933826357164e-05, + "loss": 3.7209, + "step": 528384 + }, + { + "epoch": 0.02, + "learning_rate": 4.1340968694864856e-05, + "loss": 3.7105, + "step": 528896 + }, + { + "epoch": 0.02, + "learning_rate": 4.133258274735433e-05, + "loss": 3.7326, + "step": 529408 + }, + { + "epoch": 0.02, + "learning_rate": 4.132419679984381e-05, + "loss": 3.7015, + "step": 529920 + }, + { + "epoch": 0.02, + "learning_rate": 4.131581085233329e-05, + "loss": 3.7219, + "step": 530432 + }, + { + "epoch": 0.02, + "learning_rate": 4.1307441283626505e-05, + "loss": 3.7139, + "step": 530944 + }, + { + "epoch": 0.02, + "learning_rate": 4.1299055336115985e-05, + "loss": 3.712, + "step": 531456 + }, + { + "epoch": 0.02, + "learning_rate": 4.1290669388605465e-05, + "loss": 3.7169, + "step": 531968 + }, + { + "epoch": 0.02, + "learning_rate": 4.1282283441094945e-05, + "loss": 3.7153, + "step": 532480 + }, + { + "epoch": 0.02, + "learning_rate": 4.1273913872388154e-05, + "loss": 3.7221, + "step": 532992 + }, + { + "epoch": 0.02, + "learning_rate": 4.1265527924877634e-05, + "loss": 3.6987, + "step": 533504 + }, + { + "epoch": 0.02, + "learning_rate": 4.1257141977367114e-05, + "loss": 3.7172, + "step": 534016 + }, + { + "epoch": 0.03, + "eval_loss": 3.857776165008545, + "eval_runtime": 331.1709, + "eval_samples_per_second": 1152.248, + "eval_steps_per_second": 36.009, + "step": 534240 + }, + { + "epoch": 1.0, + "learning_rate": 4.1248756029856594e-05, + "loss": 3.7143, + "step": 534528 + }, + { + "epoch": 1.0, + "learning_rate": 4.1240370082346074e-05, + "loss": 3.7012, + "step": 535040 + }, + { + "epoch": 1.0, + "learning_rate": 4.123200051363928e-05, + "loss": 3.7128, + "step": 535552 + }, + { + "epoch": 1.0, + "learning_rate": 4.122361456612876e-05, + "loss": 3.7133, + "step": 536064 + }, + { + "epoch": 1.0, + "learning_rate": 4.121522861861824e-05, + "loss": 3.7241, + "step": 536576 + }, + { + "epoch": 1.0, + "learning_rate": 4.120684267110773e-05, + "loss": 3.7115, + "step": 537088 + }, + { + "epoch": 1.0, + "learning_rate": 4.119847310240094e-05, + "loss": 3.7025, + "step": 537600 + }, + { + "epoch": 1.0, + "learning_rate": 4.119008715489042e-05, + "loss": 3.7042, + "step": 538112 + }, + { + "epoch": 1.0, + "learning_rate": 4.11817012073799e-05, + "loss": 3.7093, + "step": 538624 + }, + { + "epoch": 1.0, + "learning_rate": 4.117331525986938e-05, + "loss": 3.7148, + "step": 539136 + }, + { + "epoch": 1.0, + "learning_rate": 4.116494569116259e-05, + "loss": 3.7108, + "step": 539648 + }, + { + "epoch": 1.0, + "learning_rate": 4.115655974365207e-05, + "loss": 3.7122, + "step": 540160 + }, + { + "epoch": 1.0, + "learning_rate": 4.114817379614155e-05, + "loss": 3.7064, + "step": 540672 + }, + { + "epoch": 1.0, + "learning_rate": 4.113978784863103e-05, + "loss": 3.7061, + "step": 541184 + }, + { + "epoch": 1.0, + "learning_rate": 4.113140190112051e-05, + "loss": 3.6985, + "step": 541696 + }, + { + "epoch": 1.0, + "learning_rate": 4.1123032332413716e-05, + "loss": 3.7009, + "step": 542208 + }, + { + "epoch": 1.0, + "learning_rate": 4.1114646384903196e-05, + "loss": 3.7012, + "step": 542720 + }, + { + "epoch": 1.0, + "learning_rate": 4.110626043739268e-05, + "loss": 3.702, + "step": 543232 + }, + { + "epoch": 1.0, + "learning_rate": 4.109787448988216e-05, + "loss": 3.7052, + "step": 543744 + }, + { + "epoch": 1.0, + "learning_rate": 4.108948854237164e-05, + "loss": 3.7148, + "step": 544256 + }, + { + "epoch": 1.0, + "learning_rate": 4.108111897366485e-05, + "loss": 3.7095, + "step": 544768 + }, + { + "epoch": 1.0, + "learning_rate": 4.107273302615433e-05, + "loss": 3.7124, + "step": 545280 + }, + { + "epoch": 1.0, + "learning_rate": 4.106434707864381e-05, + "loss": 3.703, + "step": 545792 + }, + { + "epoch": 1.0, + "learning_rate": 4.105596113113329e-05, + "loss": 3.71, + "step": 546304 + }, + { + "epoch": 1.0, + "learning_rate": 4.10475915624265e-05, + "loss": 3.6961, + "step": 546816 + }, + { + "epoch": 1.0, + "learning_rate": 4.103920561491598e-05, + "loss": 3.7168, + "step": 547328 + }, + { + "epoch": 1.0, + "learning_rate": 4.103081966740546e-05, + "loss": 3.6997, + "step": 547840 + }, + { + "epoch": 1.0, + "learning_rate": 4.102243371989494e-05, + "loss": 3.6961, + "step": 548352 + }, + { + "epoch": 1.0, + "learning_rate": 4.101406415118815e-05, + "loss": 3.6968, + "step": 548864 + }, + { + "epoch": 1.0, + "learning_rate": 4.1005678203677637e-05, + "loss": 3.6995, + "step": 549376 + }, + { + "epoch": 1.01, + "learning_rate": 4.0997292256167117e-05, + "loss": 3.7002, + "step": 549888 + }, + { + "epoch": 1.01, + "learning_rate": 4.0988906308656597e-05, + "loss": 3.7102, + "step": 550400 + }, + { + "epoch": 1.01, + "learning_rate": 4.0980536739949806e-05, + "loss": 3.7111, + "step": 550912 + }, + { + "epoch": 1.01, + "learning_rate": 4.0972150792439286e-05, + "loss": 3.7075, + "step": 551424 + }, + { + "epoch": 1.01, + "learning_rate": 4.0963764844928766e-05, + "loss": 3.6999, + "step": 551936 + }, + { + "epoch": 1.01, + "learning_rate": 4.0955378897418245e-05, + "loss": 3.7105, + "step": 552448 + }, + { + "epoch": 1.01, + "learning_rate": 4.0947009328711455e-05, + "loss": 3.709, + "step": 552960 + }, + { + "epoch": 1.01, + "learning_rate": 4.0938623381200935e-05, + "loss": 3.69, + "step": 553472 + }, + { + "epoch": 1.01, + "learning_rate": 4.0930237433690414e-05, + "loss": 3.6917, + "step": 553984 + }, + { + "epoch": 1.01, + "learning_rate": 4.0921851486179894e-05, + "loss": 3.6949, + "step": 554496 + }, + { + "epoch": 1.01, + "learning_rate": 4.0913481917473104e-05, + "loss": 3.6997, + "step": 555008 + }, + { + "epoch": 1.01, + "learning_rate": 4.0905095969962583e-05, + "loss": 3.703, + "step": 555520 + }, + { + "epoch": 1.01, + "learning_rate": 4.089671002245207e-05, + "loss": 3.699, + "step": 556032 + }, + { + "epoch": 1.01, + "learning_rate": 4.088832407494155e-05, + "loss": 3.695, + "step": 556544 + }, + { + "epoch": 1.01, + "learning_rate": 4.087995450623476e-05, + "loss": 3.7077, + "step": 557056 + }, + { + "epoch": 1.01, + "learning_rate": 4.087156855872424e-05, + "loss": 3.698, + "step": 557568 + }, + { + "epoch": 1.01, + "learning_rate": 4.086318261121372e-05, + "loss": 3.6991, + "step": 558080 + }, + { + "epoch": 1.01, + "learning_rate": 4.08547966637032e-05, + "loss": 3.6843, + "step": 558592 + }, + { + "epoch": 1.01, + "learning_rate": 4.084642709499641e-05, + "loss": 3.6822, + "step": 559104 + }, + { + "epoch": 1.01, + "learning_rate": 4.083804114748589e-05, + "loss": 3.7076, + "step": 559616 + }, + { + "epoch": 1.01, + "learning_rate": 4.082965519997537e-05, + "loss": 3.6956, + "step": 560128 + }, + { + "epoch": 1.01, + "learning_rate": 4.082126925246485e-05, + "loss": 3.6998, + "step": 560640 + }, + { + "epoch": 1.01, + "learning_rate": 4.081289968375806e-05, + "loss": 3.6915, + "step": 561152 + }, + { + "epoch": 1.01, + "learning_rate": 4.080451373624754e-05, + "loss": 3.6938, + "step": 561664 + }, + { + "epoch": 1.01, + "learning_rate": 4.0796127788737024e-05, + "loss": 3.6796, + "step": 562176 + }, + { + "epoch": 1.01, + "learning_rate": 4.0787741841226504e-05, + "loss": 3.6982, + "step": 562688 + }, + { + "epoch": 1.01, + "learning_rate": 4.077937227251971e-05, + "loss": 3.6894, + "step": 563200 + }, + { + "epoch": 1.01, + "learning_rate": 4.077098632500919e-05, + "loss": 3.6905, + "step": 563712 + }, + { + "epoch": 1.01, + "learning_rate": 4.076260037749867e-05, + "loss": 3.7025, + "step": 564224 + }, + { + "epoch": 1.01, + "learning_rate": 4.075421442998815e-05, + "loss": 3.6901, + "step": 564736 + }, + { + "epoch": 1.01, + "learning_rate": 4.074584486128136e-05, + "loss": 3.6836, + "step": 565248 + }, + { + "epoch": 1.01, + "learning_rate": 4.073745891377084e-05, + "loss": 3.7005, + "step": 565760 + }, + { + "epoch": 1.01, + "learning_rate": 4.072907296626032e-05, + "loss": 3.685, + "step": 566272 + }, + { + "epoch": 1.01, + "learning_rate": 4.07206870187498e-05, + "loss": 3.6846, + "step": 566784 + }, + { + "epoch": 1.01, + "learning_rate": 4.071231745004301e-05, + "loss": 3.7004, + "step": 567296 + }, + { + "epoch": 1.01, + "learning_rate": 4.070393150253249e-05, + "loss": 3.6943, + "step": 567808 + }, + { + "epoch": 1.01, + "learning_rate": 4.069554555502198e-05, + "loss": 3.68, + "step": 568320 + }, + { + "epoch": 1.01, + "learning_rate": 4.068715960751146e-05, + "loss": 3.6936, + "step": 568832 + }, + { + "epoch": 1.01, + "learning_rate": 4.0678790038804667e-05, + "loss": 3.6815, + "step": 569344 + }, + { + "epoch": 1.01, + "learning_rate": 4.0670404091294147e-05, + "loss": 3.6837, + "step": 569856 + }, + { + "epoch": 1.01, + "learning_rate": 4.0662018143783627e-05, + "loss": 3.7005, + "step": 570368 + }, + { + "epoch": 1.01, + "learning_rate": 4.0653632196273106e-05, + "loss": 3.6977, + "step": 570880 + }, + { + "epoch": 1.01, + "learning_rate": 4.0645262627566316e-05, + "loss": 3.6999, + "step": 571392 + }, + { + "epoch": 1.01, + "learning_rate": 4.0636876680055796e-05, + "loss": 3.6961, + "step": 571904 + }, + { + "epoch": 1.01, + "learning_rate": 4.0628490732545275e-05, + "loss": 3.709, + "step": 572416 + }, + { + "epoch": 1.01, + "learning_rate": 4.0620104785034755e-05, + "loss": 3.6872, + "step": 572928 + }, + { + "epoch": 1.01, + "learning_rate": 4.0611735216327965e-05, + "loss": 3.6955, + "step": 573440 + }, + { + "epoch": 1.01, + "learning_rate": 4.0603349268817444e-05, + "loss": 3.7014, + "step": 573952 + }, + { + "epoch": 1.01, + "learning_rate": 4.059496332130693e-05, + "loss": 3.6831, + "step": 574464 + }, + { + "epoch": 1.01, + "learning_rate": 4.0586577373796404e-05, + "loss": 3.6915, + "step": 574976 + }, + { + "epoch": 1.01, + "learning_rate": 4.0578191426285884e-05, + "loss": 3.7007, + "step": 575488 + }, + { + "epoch": 1.01, + "learning_rate": 4.05698218575791e-05, + "loss": 3.7008, + "step": 576000 + }, + { + "epoch": 1.01, + "learning_rate": 4.056143591006858e-05, + "loss": 3.6948, + "step": 576512 + }, + { + "epoch": 1.01, + "learning_rate": 4.055304996255805e-05, + "loss": 3.6829, + "step": 577024 + }, + { + "epoch": 1.01, + "learning_rate": 4.054466401504753e-05, + "loss": 3.6777, + "step": 577536 + }, + { + "epoch": 1.01, + "learning_rate": 4.053629444634075e-05, + "loss": 3.6917, + "step": 578048 + }, + { + "epoch": 1.01, + "learning_rate": 4.052790849883023e-05, + "loss": 3.7, + "step": 578560 + }, + { + "epoch": 1.01, + "learning_rate": 4.05195225513197e-05, + "loss": 3.6939, + "step": 579072 + }, + { + "epoch": 1.01, + "learning_rate": 4.051113660380918e-05, + "loss": 3.6922, + "step": 579584 + }, + { + "epoch": 1.02, + "learning_rate": 4.05027670351024e-05, + "loss": 3.679, + "step": 580096 + }, + { + "epoch": 1.02, + "learning_rate": 4.049438108759188e-05, + "loss": 3.689, + "step": 580608 + }, + { + "epoch": 1.02, + "learning_rate": 4.048599514008136e-05, + "loss": 3.6833, + "step": 581120 + }, + { + "epoch": 1.02, + "learning_rate": 4.047760919257084e-05, + "loss": 3.6909, + "step": 581632 + }, + { + "epoch": 1.02, + "learning_rate": 4.0469239623864054e-05, + "loss": 3.6939, + "step": 582144 + }, + { + "epoch": 1.02, + "learning_rate": 4.046085367635353e-05, + "loss": 3.7074, + "step": 582656 + }, + { + "epoch": 1.02, + "learning_rate": 4.045246772884301e-05, + "loss": 3.6961, + "step": 583168 + }, + { + "epoch": 1.02, + "learning_rate": 4.044408178133249e-05, + "loss": 3.6816, + "step": 583680 + }, + { + "epoch": 1.02, + "learning_rate": 4.04357122126257e-05, + "loss": 3.688, + "step": 584192 + }, + { + "epoch": 1.02, + "learning_rate": 4.0427326265115176e-05, + "loss": 3.687, + "step": 584704 + }, + { + "epoch": 1.02, + "learning_rate": 4.0418940317604656e-05, + "loss": 3.6985, + "step": 585216 + }, + { + "epoch": 1.02, + "learning_rate": 4.0410554370094136e-05, + "loss": 3.6875, + "step": 585728 + }, + { + "epoch": 1.02, + "learning_rate": 4.040218480138735e-05, + "loss": 3.6991, + "step": 586240 + }, + { + "epoch": 1.02, + "learning_rate": 4.039379885387683e-05, + "loss": 3.689, + "step": 586752 + }, + { + "epoch": 1.02, + "learning_rate": 4.038541290636631e-05, + "loss": 3.6771, + "step": 587264 + }, + { + "epoch": 1.02, + "learning_rate": 4.037702695885579e-05, + "loss": 3.6884, + "step": 587776 + }, + { + "epoch": 1.02, + "learning_rate": 4.0368657390149e-05, + "loss": 3.6805, + "step": 588288 + }, + { + "epoch": 1.02, + "learning_rate": 4.036027144263848e-05, + "loss": 3.6802, + "step": 588800 + }, + { + "epoch": 1.02, + "learning_rate": 4.035188549512796e-05, + "loss": 3.6932, + "step": 589312 + }, + { + "epoch": 1.02, + "learning_rate": 4.034349954761744e-05, + "loss": 3.686, + "step": 589824 + }, + { + "epoch": 1.02, + "learning_rate": 4.033512997891065e-05, + "loss": 3.68, + "step": 590336 + }, + { + "epoch": 1.02, + "learning_rate": 4.032674403140013e-05, + "loss": 3.6837, + "step": 590848 + }, + { + "epoch": 1.02, + "learning_rate": 4.031835808388961e-05, + "loss": 3.6801, + "step": 591360 + }, + { + "epoch": 1.02, + "learning_rate": 4.030997213637909e-05, + "loss": 3.6914, + "step": 591872 + }, + { + "epoch": 1.02, + "learning_rate": 4.0301602567672305e-05, + "loss": 3.6829, + "step": 592384 + }, + { + "epoch": 1.02, + "learning_rate": 4.0293216620161785e-05, + "loss": 3.7019, + "step": 592896 + }, + { + "epoch": 1.02, + "learning_rate": 4.0284830672651265e-05, + "loss": 3.6966, + "step": 593408 + }, + { + "epoch": 1.02, + "learning_rate": 4.0276444725140745e-05, + "loss": 3.6938, + "step": 593920 + }, + { + "epoch": 1.02, + "learning_rate": 4.0268075156433954e-05, + "loss": 3.6875, + "step": 594432 + }, + { + "epoch": 1.02, + "learning_rate": 4.0259689208923434e-05, + "loss": 3.6763, + "step": 594944 + }, + { + "epoch": 1.02, + "learning_rate": 4.0251303261412914e-05, + "loss": 3.6898, + "step": 595456 + }, + { + "epoch": 1.02, + "learning_rate": 4.0242917313902394e-05, + "loss": 3.6876, + "step": 595968 + }, + { + "epoch": 1.02, + "learning_rate": 4.0234547745195603e-05, + "loss": 3.6803, + "step": 596480 + }, + { + "epoch": 1.02, + "learning_rate": 4.022616179768508e-05, + "loss": 3.6769, + "step": 596992 + }, + { + "epoch": 1.02, + "learning_rate": 4.021777585017456e-05, + "loss": 3.6897, + "step": 597504 + }, + { + "epoch": 1.02, + "learning_rate": 4.020940628146778e-05, + "loss": 3.6774, + "step": 598016 + }, + { + "epoch": 1.02, + "learning_rate": 4.020102033395726e-05, + "loss": 3.6865, + "step": 598528 + }, + { + "epoch": 1.02, + "learning_rate": 4.019263438644674e-05, + "loss": 3.6773, + "step": 599040 + }, + { + "epoch": 1.02, + "learning_rate": 4.018424843893622e-05, + "loss": 3.6908, + "step": 599552 + }, + { + "epoch": 1.02, + "learning_rate": 4.01758624914257e-05, + "loss": 3.6745, + "step": 600064 + }, + { + "epoch": 1.02, + "learning_rate": 4.016749292271891e-05, + "loss": 3.6979, + "step": 600576 + }, + { + "epoch": 1.02, + "learning_rate": 4.015910697520839e-05, + "loss": 3.6866, + "step": 601088 + }, + { + "epoch": 1.02, + "learning_rate": 4.015072102769787e-05, + "loss": 3.6958, + "step": 601600 + }, + { + "epoch": 1.02, + "learning_rate": 4.014233508018735e-05, + "loss": 3.672, + "step": 602112 + }, + { + "epoch": 1.02, + "learning_rate": 4.013396551148056e-05, + "loss": 3.6924, + "step": 602624 + }, + { + "epoch": 1.02, + "learning_rate": 4.012557956397004e-05, + "loss": 3.6868, + "step": 603136 + }, + { + "epoch": 1.02, + "learning_rate": 4.011719361645952e-05, + "loss": 3.6926, + "step": 603648 + }, + { + "epoch": 1.02, + "learning_rate": 4.0108807668949e-05, + "loss": 3.6856, + "step": 604160 + }, + { + "epoch": 1.02, + "learning_rate": 4.010043810024221e-05, + "loss": 3.6855, + "step": 604672 + }, + { + "epoch": 1.02, + "learning_rate": 4.009205215273169e-05, + "loss": 3.6859, + "step": 605184 + }, + { + "epoch": 1.02, + "learning_rate": 4.008366620522117e-05, + "loss": 3.6989, + "step": 605696 + }, + { + "epoch": 1.02, + "learning_rate": 4.007528025771065e-05, + "loss": 3.6743, + "step": 606208 + }, + { + "epoch": 1.02, + "learning_rate": 4.006691068900386e-05, + "loss": 3.6887, + "step": 606720 + }, + { + "epoch": 1.02, + "learning_rate": 4.005852474149334e-05, + "loss": 3.6842, + "step": 607232 + }, + { + "epoch": 1.02, + "learning_rate": 4.005013879398282e-05, + "loss": 3.6799, + "step": 607744 + }, + { + "epoch": 1.02, + "learning_rate": 4.00417528464723e-05, + "loss": 3.6863, + "step": 608256 + }, + { + "epoch": 1.02, + "learning_rate": 4.003338327776551e-05, + "loss": 3.6821, + "step": 608768 + }, + { + "epoch": 1.02, + "learning_rate": 4.002499733025499e-05, + "loss": 3.6945, + "step": 609280 + }, + { + "epoch": 1.02, + "learning_rate": 4.001661138274447e-05, + "loss": 3.6675, + "step": 609792 + }, + { + "epoch": 1.02, + "learning_rate": 4.000822543523395e-05, + "loss": 3.6886, + "step": 610304 + }, + { + "epoch": 1.03, + "eval_loss": 3.850329637527466, + "eval_runtime": 330.7284, + "eval_samples_per_second": 1153.79, + "eval_steps_per_second": 36.057, + "step": 610560 + }, + { + "epoch": 0.0, + "learning_rate": 3.9999855866527166e-05, + "loss": 3.6789, + "step": 610816 + }, + { + "epoch": 0.0, + "learning_rate": 3.9991469919016646e-05, + "loss": 3.6738, + "step": 611328 + }, + { + "epoch": 0.0, + "learning_rate": 3.9983083971506126e-05, + "loss": 3.68, + "step": 611840 + }, + { + "epoch": 0.0, + "learning_rate": 3.9974698023995606e-05, + "loss": 3.6814, + "step": 612352 + }, + { + "epoch": 0.0, + "learning_rate": 3.9966328455288815e-05, + "loss": 3.6972, + "step": 612864 + }, + { + "epoch": 0.0, + "learning_rate": 3.9957942507778295e-05, + "loss": 3.6773, + "step": 613376 + }, + { + "epoch": 0.0, + "learning_rate": 3.9949556560267775e-05, + "loss": 3.6776, + "step": 613888 + }, + { + "epoch": 0.0, + "learning_rate": 3.9941170612757255e-05, + "loss": 3.6751, + "step": 614400 + }, + { + "epoch": 0.0, + "learning_rate": 3.9932801044050464e-05, + "loss": 3.6751, + "step": 614912 + }, + { + "epoch": 0.0, + "learning_rate": 3.9924415096539944e-05, + "loss": 3.6874, + "step": 615424 + }, + { + "epoch": 0.0, + "learning_rate": 3.9916029149029424e-05, + "loss": 3.678, + "step": 615936 + }, + { + "epoch": 0.0, + "learning_rate": 3.9907643201518904e-05, + "loss": 3.6844, + "step": 616448 + }, + { + "epoch": 0.0, + "learning_rate": 3.989927363281212e-05, + "loss": 3.6743, + "step": 616960 + }, + { + "epoch": 0.0, + "learning_rate": 3.98908876853016e-05, + "loss": 3.6741, + "step": 617472 + }, + { + "epoch": 0.0, + "learning_rate": 3.988250173779108e-05, + "loss": 3.6724, + "step": 617984 + }, + { + "epoch": 0.0, + "learning_rate": 3.987411579028056e-05, + "loss": 3.6718, + "step": 618496 + }, + { + "epoch": 0.0, + "learning_rate": 3.986574622157377e-05, + "loss": 3.6693, + "step": 619008 + }, + { + "epoch": 0.0, + "learning_rate": 3.985736027406325e-05, + "loss": 3.6736, + "step": 619520 + }, + { + "epoch": 0.0, + "learning_rate": 3.984897432655273e-05, + "loss": 3.6758, + "step": 620032 + }, + { + "epoch": 0.0, + "learning_rate": 3.984058837904221e-05, + "loss": 3.6831, + "step": 620544 + }, + { + "epoch": 0.0, + "learning_rate": 3.983221881033542e-05, + "loss": 3.6815, + "step": 621056 + }, + { + "epoch": 0.0, + "learning_rate": 3.98238328628249e-05, + "loss": 3.6862, + "step": 621568 + }, + { + "epoch": 0.0, + "learning_rate": 3.981544691531438e-05, + "loss": 3.6697, + "step": 622080 + }, + { + "epoch": 0.0, + "learning_rate": 3.980706096780386e-05, + "loss": 3.6788, + "step": 622592 + }, + { + "epoch": 0.0, + "learning_rate": 3.979867502029334e-05, + "loss": 3.6705, + "step": 623104 + }, + { + "epoch": 0.0, + "learning_rate": 3.9790305451586554e-05, + "loss": 3.6843, + "step": 623616 + }, + { + "epoch": 0.0, + "learning_rate": 3.9781919504076034e-05, + "loss": 3.673, + "step": 624128 + }, + { + "epoch": 0.0, + "learning_rate": 3.9773533556565514e-05, + "loss": 3.6702, + "step": 624640 + }, + { + "epoch": 0.0, + "learning_rate": 3.9765147609054994e-05, + "loss": 3.6657, + "step": 625152 + }, + { + "epoch": 0.0, + "learning_rate": 3.97567780403482e-05, + "loss": 3.6674, + "step": 625664 + }, + { + "epoch": 0.01, + "learning_rate": 3.974839209283768e-05, + "loss": 3.6667, + "step": 626176 + }, + { + "epoch": 0.01, + "learning_rate": 3.974000614532716e-05, + "loss": 3.6823, + "step": 626688 + }, + { + "epoch": 0.01, + "learning_rate": 3.973162019781664e-05, + "loss": 3.678, + "step": 627200 + }, + { + "epoch": 0.01, + "learning_rate": 3.972325062910985e-05, + "loss": 3.6798, + "step": 627712 + }, + { + "epoch": 0.01, + "learning_rate": 3.971486468159933e-05, + "loss": 3.6701, + "step": 628224 + }, + { + "epoch": 0.01, + "learning_rate": 3.970647873408881e-05, + "loss": 3.6817, + "step": 628736 + }, + { + "epoch": 0.01, + "learning_rate": 3.969809278657829e-05, + "loss": 3.68, + "step": 629248 + }, + { + "epoch": 0.01, + "learning_rate": 3.968972321787151e-05, + "loss": 3.6628, + "step": 629760 + }, + { + "epoch": 0.01, + "learning_rate": 3.968133727036099e-05, + "loss": 3.6644, + "step": 630272 + }, + { + "epoch": 0.01, + "learning_rate": 3.967295132285047e-05, + "loss": 3.6659, + "step": 630784 + }, + { + "epoch": 0.01, + "learning_rate": 3.966456537533995e-05, + "loss": 3.6682, + "step": 631296 + }, + { + "epoch": 0.01, + "learning_rate": 3.9656195806633156e-05, + "loss": 3.6731, + "step": 631808 + }, + { + "epoch": 0.01, + "learning_rate": 3.9647809859122636e-05, + "loss": 3.6701, + "step": 632320 + }, + { + "epoch": 0.01, + "learning_rate": 3.9639423911612116e-05, + "loss": 3.6655, + "step": 632832 + }, + { + "epoch": 0.01, + "learning_rate": 3.9631037964101596e-05, + "loss": 3.6785, + "step": 633344 + }, + { + "epoch": 0.01, + "learning_rate": 3.9622668395394805e-05, + "loss": 3.6664, + "step": 633856 + }, + { + "epoch": 0.01, + "learning_rate": 3.9614282447884285e-05, + "loss": 3.6717, + "step": 634368 + }, + { + "epoch": 0.01, + "learning_rate": 3.9605896500373765e-05, + "loss": 3.6574, + "step": 634880 + }, + { + "epoch": 0.01, + "learning_rate": 3.9597510552863245e-05, + "loss": 3.6472, + "step": 635392 + }, + { + "epoch": 0.01, + "learning_rate": 3.958914098415646e-05, + "loss": 3.6797, + "step": 635904 + }, + { + "epoch": 0.01, + "learning_rate": 3.958075503664594e-05, + "loss": 3.6678, + "step": 636416 + }, + { + "epoch": 0.01, + "learning_rate": 3.957236908913542e-05, + "loss": 3.6723, + "step": 636928 + }, + { + "epoch": 0.01, + "learning_rate": 3.95639831416249e-05, + "loss": 3.6633, + "step": 637440 + }, + { + "epoch": 0.01, + "learning_rate": 3.955561357291811e-05, + "loss": 3.661, + "step": 637952 + }, + { + "epoch": 0.01, + "learning_rate": 3.954722762540759e-05, + "loss": 3.656, + "step": 638464 + }, + { + "epoch": 0.01, + "learning_rate": 3.953884167789707e-05, + "loss": 3.6687, + "step": 638976 + }, + { + "epoch": 0.01, + "learning_rate": 3.953045573038655e-05, + "loss": 3.6595, + "step": 639488 + }, + { + "epoch": 0.01, + "learning_rate": 3.952208616167976e-05, + "loss": 3.6658, + "step": 640000 + }, + { + "epoch": 0.01, + "learning_rate": 3.951370021416924e-05, + "loss": 3.6744, + "step": 640512 + }, + { + "epoch": 0.01, + "learning_rate": 3.950531426665872e-05, + "loss": 3.6574, + "step": 641024 + }, + { + "epoch": 0.01, + "learning_rate": 3.94969283191482e-05, + "loss": 3.6567, + "step": 641536 + }, + { + "epoch": 0.01, + "learning_rate": 3.9488558750441415e-05, + "loss": 3.6733, + "step": 642048 + }, + { + "epoch": 0.01, + "learning_rate": 3.9480172802930895e-05, + "loss": 3.6563, + "step": 642560 + }, + { + "epoch": 0.01, + "learning_rate": 3.9471786855420375e-05, + "loss": 3.6569, + "step": 643072 + }, + { + "epoch": 0.01, + "learning_rate": 3.946340090790985e-05, + "loss": 3.6735, + "step": 643584 + }, + { + "epoch": 0.01, + "learning_rate": 3.945501496039933e-05, + "loss": 3.6618, + "step": 644096 + }, + { + "epoch": 0.01, + "learning_rate": 3.9446645391692544e-05, + "loss": 3.6543, + "step": 644608 + }, + { + "epoch": 0.01, + "learning_rate": 3.9438259444182024e-05, + "loss": 3.6641, + "step": 645120 + }, + { + "epoch": 0.01, + "learning_rate": 3.94298734966715e-05, + "loss": 3.6528, + "step": 645632 + }, + { + "epoch": 0.01, + "learning_rate": 3.942148754916098e-05, + "loss": 3.654, + "step": 646144 + }, + { + "epoch": 0.01, + "learning_rate": 3.941311798045419e-05, + "loss": 3.6746, + "step": 646656 + }, + { + "epoch": 0.01, + "learning_rate": 3.940473203294367e-05, + "loss": 3.6666, + "step": 647168 + }, + { + "epoch": 0.01, + "learning_rate": 3.939634608543315e-05, + "loss": 3.6712, + "step": 647680 + }, + { + "epoch": 0.01, + "learning_rate": 3.938796013792263e-05, + "loss": 3.6664, + "step": 648192 + }, + { + "epoch": 0.01, + "learning_rate": 3.937959056921585e-05, + "loss": 3.6845, + "step": 648704 + }, + { + "epoch": 0.01, + "learning_rate": 3.937120462170532e-05, + "loss": 3.6574, + "step": 649216 + }, + { + "epoch": 0.01, + "learning_rate": 3.93628186741948e-05, + "loss": 3.6703, + "step": 649728 + }, + { + "epoch": 0.01, + "learning_rate": 3.935443272668428e-05, + "loss": 3.6694, + "step": 650240 + }, + { + "epoch": 0.01, + "learning_rate": 3.93460631579775e-05, + "loss": 3.6591, + "step": 650752 + }, + { + "epoch": 0.01, + "learning_rate": 3.933767721046697e-05, + "loss": 3.6592, + "step": 651264 + }, + { + "epoch": 0.01, + "learning_rate": 3.932929126295645e-05, + "loss": 3.6766, + "step": 651776 + }, + { + "epoch": 0.01, + "learning_rate": 3.932090531544593e-05, + "loss": 3.6699, + "step": 652288 + }, + { + "epoch": 0.01, + "learning_rate": 3.9312535746739146e-05, + "loss": 3.6716, + "step": 652800 + }, + { + "epoch": 0.01, + "learning_rate": 3.9304149799228626e-05, + "loss": 3.653, + "step": 653312 + }, + { + "epoch": 0.01, + "learning_rate": 3.9295763851718106e-05, + "loss": 3.647, + "step": 653824 + }, + { + "epoch": 0.01, + "learning_rate": 3.9287377904207586e-05, + "loss": 3.667, + "step": 654336 + }, + { + "epoch": 0.01, + "learning_rate": 3.9279008335500795e-05, + "loss": 3.6731, + "step": 654848 + }, + { + "epoch": 0.01, + "learning_rate": 3.9270622387990275e-05, + "loss": 3.6676, + "step": 655360 + }, + { + "epoch": 0.01, + "learning_rate": 3.9262236440479755e-05, + "loss": 3.6653, + "step": 655872 + }, + { + "epoch": 0.02, + "learning_rate": 3.9253850492969235e-05, + "loss": 3.6515, + "step": 656384 + }, + { + "epoch": 0.02, + "learning_rate": 3.9245464545458715e-05, + "loss": 3.6613, + "step": 656896 + }, + { + "epoch": 0.02, + "learning_rate": 3.9237094976751924e-05, + "loss": 3.6564, + "step": 657408 + }, + { + "epoch": 0.02, + "learning_rate": 3.9228709029241404e-05, + "loss": 3.6585, + "step": 657920 + }, + { + "epoch": 0.02, + "learning_rate": 3.9220323081730884e-05, + "loss": 3.6706, + "step": 658432 + }, + { + "epoch": 0.02, + "learning_rate": 3.9211937134220364e-05, + "loss": 3.6775, + "step": 658944 + }, + { + "epoch": 0.02, + "learning_rate": 3.920356756551358e-05, + "loss": 3.6698, + "step": 659456 + }, + { + "epoch": 0.02, + "learning_rate": 3.919518161800306e-05, + "loss": 3.6577, + "step": 659968 + }, + { + "epoch": 0.02, + "learning_rate": 3.918679567049254e-05, + "loss": 3.6568, + "step": 660480 + }, + { + "epoch": 0.02, + "learning_rate": 3.917840972298202e-05, + "loss": 3.6618, + "step": 660992 + }, + { + "epoch": 0.02, + "learning_rate": 3.917004015427523e-05, + "loss": 3.6693, + "step": 661504 + }, + { + "epoch": 0.02, + "learning_rate": 3.916165420676471e-05, + "loss": 3.6595, + "step": 662016 + }, + { + "epoch": 0.02, + "learning_rate": 3.915326825925419e-05, + "loss": 3.6717, + "step": 662528 + }, + { + "epoch": 0.02, + "learning_rate": 3.914488231174367e-05, + "loss": 3.6612, + "step": 663040 + }, + { + "epoch": 0.02, + "learning_rate": 3.913651274303688e-05, + "loss": 3.6533, + "step": 663552 + }, + { + "epoch": 0.02, + "learning_rate": 3.912812679552636e-05, + "loss": 3.6603, + "step": 664064 + }, + { + "epoch": 0.02, + "learning_rate": 3.911974084801584e-05, + "loss": 3.6524, + "step": 664576 + }, + { + "epoch": 0.02, + "learning_rate": 3.911135490050532e-05, + "loss": 3.6538, + "step": 665088 + }, + { + "epoch": 0.02, + "learning_rate": 3.9102985331798534e-05, + "loss": 3.6653, + "step": 665600 + }, + { + "epoch": 0.02, + "learning_rate": 3.9094599384288014e-05, + "loss": 3.6601, + "step": 666112 + }, + { + "epoch": 0.02, + "learning_rate": 3.9086213436777494e-05, + "loss": 3.6529, + "step": 666624 + }, + { + "epoch": 0.02, + "learning_rate": 3.9077827489266973e-05, + "loss": 3.6531, + "step": 667136 + }, + { + "epoch": 0.02, + "learning_rate": 3.906945792056018e-05, + "loss": 3.652, + "step": 667648 + }, + { + "epoch": 0.02, + "learning_rate": 3.906107197304966e-05, + "loss": 3.6668, + "step": 668160 + }, + { + "epoch": 0.02, + "learning_rate": 3.905268602553914e-05, + "loss": 3.6533, + "step": 668672 + }, + { + "epoch": 0.02, + "learning_rate": 3.904430007802862e-05, + "loss": 3.6768, + "step": 669184 + }, + { + "epoch": 0.02, + "learning_rate": 3.903593050932183e-05, + "loss": 3.672, + "step": 669696 + }, + { + "epoch": 0.02, + "learning_rate": 3.902754456181131e-05, + "loss": 3.6658, + "step": 670208 + }, + { + "epoch": 0.02, + "learning_rate": 3.901915861430079e-05, + "loss": 3.6579, + "step": 670720 + }, + { + "epoch": 0.02, + "learning_rate": 3.901077266679027e-05, + "loss": 3.6524, + "step": 671232 + }, + { + "epoch": 0.02, + "learning_rate": 3.900240309808349e-05, + "loss": 3.664, + "step": 671744 + }, + { + "epoch": 0.02, + "learning_rate": 3.899401715057297e-05, + "loss": 3.6587, + "step": 672256 + }, + { + "epoch": 0.02, + "learning_rate": 3.898563120306245e-05, + "loss": 3.6537, + "step": 672768 + }, + { + "epoch": 0.02, + "learning_rate": 3.897724525555193e-05, + "loss": 3.6523, + "step": 673280 + }, + { + "epoch": 0.02, + "learning_rate": 3.8968875686845136e-05, + "loss": 3.6655, + "step": 673792 + }, + { + "epoch": 0.02, + "learning_rate": 3.8960489739334616e-05, + "loss": 3.6532, + "step": 674304 + }, + { + "epoch": 0.02, + "learning_rate": 3.8952103791824096e-05, + "loss": 3.6571, + "step": 674816 + }, + { + "epoch": 0.02, + "learning_rate": 3.8943717844313576e-05, + "loss": 3.6492, + "step": 675328 + }, + { + "epoch": 0.02, + "learning_rate": 3.8935348275606785e-05, + "loss": 3.6649, + "step": 675840 + }, + { + "epoch": 0.02, + "learning_rate": 3.8926962328096265e-05, + "loss": 3.6482, + "step": 676352 + }, + { + "epoch": 0.02, + "learning_rate": 3.8918576380585745e-05, + "loss": 3.6658, + "step": 676864 + }, + { + "epoch": 0.02, + "learning_rate": 3.8910190433075225e-05, + "loss": 3.6617, + "step": 677376 + }, + { + "epoch": 0.02, + "learning_rate": 3.890182086436844e-05, + "loss": 3.6678, + "step": 677888 + }, + { + "epoch": 0.02, + "learning_rate": 3.889343491685792e-05, + "loss": 3.649, + "step": 678400 + }, + { + "epoch": 0.02, + "learning_rate": 3.88850489693474e-05, + "loss": 3.6651, + "step": 678912 + }, + { + "epoch": 0.02, + "learning_rate": 3.887666302183688e-05, + "loss": 3.6554, + "step": 679424 + }, + { + "epoch": 0.02, + "learning_rate": 3.886829345313009e-05, + "loss": 3.664, + "step": 679936 + }, + { + "epoch": 0.02, + "learning_rate": 3.885990750561957e-05, + "loss": 3.6637, + "step": 680448 + }, + { + "epoch": 0.02, + "learning_rate": 3.885152155810905e-05, + "loss": 3.6547, + "step": 680960 + }, + { + "epoch": 0.02, + "learning_rate": 3.884313561059853e-05, + "loss": 3.6613, + "step": 681472 + }, + { + "epoch": 0.02, + "learning_rate": 3.883476604189174e-05, + "loss": 3.6711, + "step": 681984 + }, + { + "epoch": 0.02, + "learning_rate": 3.882638009438122e-05, + "loss": 3.6478, + "step": 682496 + }, + { + "epoch": 0.02, + "learning_rate": 3.88179941468707e-05, + "loss": 3.6598, + "step": 683008 + }, + { + "epoch": 0.02, + "learning_rate": 3.880960819936018e-05, + "loss": 3.6623, + "step": 683520 + }, + { + "epoch": 0.02, + "learning_rate": 3.8801238630653395e-05, + "loss": 3.6573, + "step": 684032 + }, + { + "epoch": 0.02, + "learning_rate": 3.8792852683142875e-05, + "loss": 3.6509, + "step": 684544 + }, + { + "epoch": 0.02, + "learning_rate": 3.8784466735632355e-05, + "loss": 3.6566, + "step": 685056 + }, + { + "epoch": 0.02, + "learning_rate": 3.8776080788121834e-05, + "loss": 3.6659, + "step": 685568 + }, + { + "epoch": 0.02, + "learning_rate": 3.8767711219415044e-05, + "loss": 3.644, + "step": 686080 + }, + { + "epoch": 0.02, + "learning_rate": 3.8759325271904524e-05, + "loss": 3.6592, + "step": 686592 + }, + { + "epoch": 0.03, + "eval_loss": 3.8463475704193115, + "eval_runtime": 309.9084, + "eval_samples_per_second": 1231.302, + "eval_steps_per_second": 38.479, + "step": 686880 + }, + { + "epoch": 1.0, + "learning_rate": 3.8750939324394004e-05, + "loss": 3.653, + "step": 687104 + }, + { + "epoch": 1.0, + "learning_rate": 3.8742553376883483e-05, + "loss": 3.647, + "step": 687616 + }, + { + "epoch": 1.0, + "learning_rate": 3.873418380817669e-05, + "loss": 3.6512, + "step": 688128 + }, + { + "epoch": 1.0, + "learning_rate": 3.872579786066617e-05, + "loss": 3.6583, + "step": 688640 + }, + { + "epoch": 1.0, + "learning_rate": 3.871741191315565e-05, + "loss": 3.6721, + "step": 689152 + }, + { + "epoch": 1.0, + "learning_rate": 3.870902596564513e-05, + "loss": 3.6506, + "step": 689664 + }, + { + "epoch": 1.0, + "learning_rate": 3.870065639693835e-05, + "loss": 3.6515, + "step": 690176 + }, + { + "epoch": 1.0, + "learning_rate": 3.869227044942783e-05, + "loss": 3.6514, + "step": 690688 + }, + { + "epoch": 1.0, + "learning_rate": 3.868388450191731e-05, + "loss": 3.6417, + "step": 691200 + }, + { + "epoch": 1.0, + "learning_rate": 3.867549855440679e-05, + "loss": 3.6646, + "step": 691712 + }, + { + "epoch": 1.0, + "learning_rate": 3.86671289857e-05, + "loss": 3.6502, + "step": 692224 + }, + { + "epoch": 1.0, + "learning_rate": 3.865874303818948e-05, + "loss": 3.6538, + "step": 692736 + }, + { + "epoch": 1.0, + "learning_rate": 3.865035709067896e-05, + "loss": 3.6579, + "step": 693248 + }, + { + "epoch": 1.0, + "learning_rate": 3.864197114316844e-05, + "loss": 3.6431, + "step": 693760 + }, + { + "epoch": 1.0, + "learning_rate": 3.8633601574461646e-05, + "loss": 3.6449, + "step": 694272 + }, + { + "epoch": 1.0, + "learning_rate": 3.8625215626951126e-05, + "loss": 3.6461, + "step": 694784 + }, + { + "epoch": 1.0, + "learning_rate": 3.8616829679440606e-05, + "loss": 3.6443, + "step": 695296 + }, + { + "epoch": 1.0, + "learning_rate": 3.8608443731930086e-05, + "loss": 3.6512, + "step": 695808 + }, + { + "epoch": 1.0, + "learning_rate": 3.86000741632233e-05, + "loss": 3.6451, + "step": 696320 + }, + { + "epoch": 1.0, + "learning_rate": 3.859168821571278e-05, + "loss": 3.6554, + "step": 696832 + }, + { + "epoch": 1.0, + "learning_rate": 3.858330226820226e-05, + "loss": 3.6562, + "step": 697344 + }, + { + "epoch": 1.0, + "learning_rate": 3.857491632069174e-05, + "loss": 3.6605, + "step": 697856 + }, + { + "epoch": 1.0, + "learning_rate": 3.856654675198495e-05, + "loss": 3.6488, + "step": 698368 + }, + { + "epoch": 1.0, + "learning_rate": 3.855816080447443e-05, + "loss": 3.646, + "step": 698880 + }, + { + "epoch": 1.0, + "learning_rate": 3.854977485696391e-05, + "loss": 3.6462, + "step": 699392 + }, + { + "epoch": 1.0, + "learning_rate": 3.854138890945339e-05, + "loss": 3.6582, + "step": 699904 + }, + { + "epoch": 1.0, + "learning_rate": 3.85330193407466e-05, + "loss": 3.6487, + "step": 700416 + }, + { + "epoch": 1.0, + "learning_rate": 3.852463339323608e-05, + "loss": 3.6443, + "step": 700928 + }, + { + "epoch": 1.0, + "learning_rate": 3.851624744572556e-05, + "loss": 3.6418, + "step": 701440 + }, + { + "epoch": 1.0, + "learning_rate": 3.850786149821504e-05, + "loss": 3.6404, + "step": 701952 + }, + { + "epoch": 1.01, + "learning_rate": 3.8499491929508256e-05, + "loss": 3.6396, + "step": 702464 + }, + { + "epoch": 1.01, + "learning_rate": 3.8491105981997736e-05, + "loss": 3.658, + "step": 702976 + }, + { + "epoch": 1.01, + "learning_rate": 3.8482720034487216e-05, + "loss": 3.6561, + "step": 703488 + }, + { + "epoch": 1.01, + "learning_rate": 3.8474334086976695e-05, + "loss": 3.6549, + "step": 704000 + }, + { + "epoch": 1.01, + "learning_rate": 3.8465964518269905e-05, + "loss": 3.645, + "step": 704512 + }, + { + "epoch": 1.01, + "learning_rate": 3.8457578570759385e-05, + "loss": 3.6488, + "step": 705024 + }, + { + "epoch": 1.01, + "learning_rate": 3.8449192623248865e-05, + "loss": 3.6588, + "step": 705536 + }, + { + "epoch": 1.01, + "learning_rate": 3.8440806675738344e-05, + "loss": 3.639, + "step": 706048 + }, + { + "epoch": 1.01, + "learning_rate": 3.8432437107031554e-05, + "loss": 3.6392, + "step": 706560 + }, + { + "epoch": 1.01, + "learning_rate": 3.8424051159521034e-05, + "loss": 3.6367, + "step": 707072 + }, + { + "epoch": 1.01, + "learning_rate": 3.8415665212010513e-05, + "loss": 3.6423, + "step": 707584 + }, + { + "epoch": 1.01, + "learning_rate": 3.8407279264499993e-05, + "loss": 3.6507, + "step": 708096 + }, + { + "epoch": 1.01, + "learning_rate": 3.839890969579321e-05, + "loss": 3.6439, + "step": 708608 + }, + { + "epoch": 1.01, + "learning_rate": 3.839052374828269e-05, + "loss": 3.6403, + "step": 709120 + }, + { + "epoch": 1.01, + "learning_rate": 3.838213780077217e-05, + "loss": 3.6523, + "step": 709632 + }, + { + "epoch": 1.01, + "learning_rate": 3.837375185326164e-05, + "loss": 3.6446, + "step": 710144 + }, + { + "epoch": 1.01, + "learning_rate": 3.836538228455486e-05, + "loss": 3.6447, + "step": 710656 + }, + { + "epoch": 1.01, + "learning_rate": 3.835699633704434e-05, + "loss": 3.635, + "step": 711168 + }, + { + "epoch": 1.01, + "learning_rate": 3.834861038953382e-05, + "loss": 3.6164, + "step": 711680 + }, + { + "epoch": 1.01, + "learning_rate": 3.834022444202329e-05, + "loss": 3.6561, + "step": 712192 + }, + { + "epoch": 1.01, + "learning_rate": 3.833185487331651e-05, + "loss": 3.6397, + "step": 712704 + }, + { + "epoch": 1.01, + "learning_rate": 3.832346892580599e-05, + "loss": 3.65, + "step": 713216 + }, + { + "epoch": 1.01, + "learning_rate": 3.831508297829547e-05, + "loss": 3.6357, + "step": 713728 + }, + { + "epoch": 1.01, + "learning_rate": 3.830669703078495e-05, + "loss": 3.6384, + "step": 714240 + }, + { + "epoch": 1.01, + "learning_rate": 3.829832746207816e-05, + "loss": 3.6304, + "step": 714752 + }, + { + "epoch": 1.01, + "learning_rate": 3.828994151456764e-05, + "loss": 3.6413, + "step": 715264 + }, + { + "epoch": 1.01, + "learning_rate": 3.8281555567057116e-05, + "loss": 3.6347, + "step": 715776 + }, + { + "epoch": 1.01, + "learning_rate": 3.8273169619546596e-05, + "loss": 3.64, + "step": 716288 + }, + { + "epoch": 1.01, + "learning_rate": 3.826480005083981e-05, + "loss": 3.6515, + "step": 716800 + }, + { + "epoch": 1.01, + "learning_rate": 3.825641410332929e-05, + "loss": 3.6329, + "step": 717312 + }, + { + "epoch": 1.01, + "learning_rate": 3.8248028155818765e-05, + "loss": 3.6299, + "step": 717824 + }, + { + "epoch": 1.01, + "learning_rate": 3.8239642208308245e-05, + "loss": 3.6503, + "step": 718336 + }, + { + "epoch": 1.01, + "learning_rate": 3.8231256260797725e-05, + "loss": 3.6331, + "step": 718848 + }, + { + "epoch": 1.01, + "learning_rate": 3.822288669209094e-05, + "loss": 3.631, + "step": 719360 + }, + { + "epoch": 1.01, + "learning_rate": 3.8214500744580414e-05, + "loss": 3.6455, + "step": 719872 + }, + { + "epoch": 1.01, + "learning_rate": 3.82061147970699e-05, + "loss": 3.64, + "step": 720384 + }, + { + "epoch": 1.01, + "learning_rate": 3.819772884955938e-05, + "loss": 3.6289, + "step": 720896 + }, + { + "epoch": 1.01, + "learning_rate": 3.818935928085259e-05, + "loss": 3.6392, + "step": 721408 + }, + { + "epoch": 1.01, + "learning_rate": 3.818097333334207e-05, + "loss": 3.627, + "step": 721920 + }, + { + "epoch": 1.01, + "learning_rate": 3.817258738583155e-05, + "loss": 3.6331, + "step": 722432 + }, + { + "epoch": 1.01, + "learning_rate": 3.816420143832103e-05, + "loss": 3.6461, + "step": 722944 + }, + { + "epoch": 1.01, + "learning_rate": 3.815583186961424e-05, + "loss": 3.6421, + "step": 723456 + }, + { + "epoch": 1.01, + "learning_rate": 3.814744592210372e-05, + "loss": 3.6484, + "step": 723968 + }, + { + "epoch": 1.01, + "learning_rate": 3.81390599745932e-05, + "loss": 3.6415, + "step": 724480 + }, + { + "epoch": 1.01, + "learning_rate": 3.813067402708268e-05, + "loss": 3.6586, + "step": 724992 + }, + { + "epoch": 1.01, + "learning_rate": 3.812230445837589e-05, + "loss": 3.6297, + "step": 725504 + }, + { + "epoch": 1.01, + "learning_rate": 3.811391851086537e-05, + "loss": 3.6498, + "step": 726016 + }, + { + "epoch": 1.01, + "learning_rate": 3.810553256335485e-05, + "loss": 3.6374, + "step": 726528 + }, + { + "epoch": 1.01, + "learning_rate": 3.8097146615844334e-05, + "loss": 3.6366, + "step": 727040 + }, + { + "epoch": 1.01, + "learning_rate": 3.8088777047137543e-05, + "loss": 3.6372, + "step": 727552 + }, + { + "epoch": 1.01, + "learning_rate": 3.8080391099627023e-05, + "loss": 3.6524, + "step": 728064 + }, + { + "epoch": 1.01, + "learning_rate": 3.80720051521165e-05, + "loss": 3.6443, + "step": 728576 + }, + { + "epoch": 1.01, + "learning_rate": 3.806361920460598e-05, + "loss": 3.6492, + "step": 729088 + }, + { + "epoch": 1.01, + "learning_rate": 3.805524963589919e-05, + "loss": 3.6271, + "step": 729600 + }, + { + "epoch": 1.01, + "learning_rate": 3.804686368838867e-05, + "loss": 3.6263, + "step": 730112 + }, + { + "epoch": 1.01, + "learning_rate": 3.803847774087815e-05, + "loss": 3.6392, + "step": 730624 + }, + { + "epoch": 1.01, + "learning_rate": 3.803009179336763e-05, + "loss": 3.6479, + "step": 731136 + }, + { + "epoch": 1.01, + "learning_rate": 3.802172222466084e-05, + "loss": 3.6374, + "step": 731648 + }, + { + "epoch": 1.01, + "learning_rate": 3.801333627715032e-05, + "loss": 3.6425, + "step": 732160 + }, + { + "epoch": 1.02, + "learning_rate": 3.80049503296398e-05, + "loss": 3.6289, + "step": 732672 + }, + { + "epoch": 1.02, + "learning_rate": 3.799656438212929e-05, + "loss": 3.6362, + "step": 733184 + }, + { + "epoch": 1.02, + "learning_rate": 3.79881948134225e-05, + "loss": 3.6335, + "step": 733696 + }, + { + "epoch": 1.02, + "learning_rate": 3.797980886591198e-05, + "loss": 3.6312, + "step": 734208 + }, + { + "epoch": 1.02, + "learning_rate": 3.797142291840146e-05, + "loss": 3.6462, + "step": 734720 + }, + { + "epoch": 1.02, + "learning_rate": 3.796303697089094e-05, + "loss": 3.652, + "step": 735232 + }, + { + "epoch": 1.02, + "learning_rate": 3.7954667402184146e-05, + "loss": 3.6471, + "step": 735744 + }, + { + "epoch": 1.02, + "learning_rate": 3.7946281454673626e-05, + "loss": 3.6315, + "step": 736256 + }, + { + "epoch": 1.02, + "learning_rate": 3.7937895507163106e-05, + "loss": 3.633, + "step": 736768 + }, + { + "epoch": 1.02, + "learning_rate": 3.7929509559652586e-05, + "loss": 3.638, + "step": 737280 + }, + { + "epoch": 1.02, + "learning_rate": 3.7921139990945795e-05, + "loss": 3.6444, + "step": 737792 + }, + { + "epoch": 1.02, + "learning_rate": 3.7912754043435275e-05, + "loss": 3.6371, + "step": 738304 + }, + { + "epoch": 1.02, + "learning_rate": 3.7904368095924755e-05, + "loss": 3.6458, + "step": 738816 + }, + { + "epoch": 1.02, + "learning_rate": 3.789599852721797e-05, + "loss": 3.6376, + "step": 739328 + }, + { + "epoch": 1.02, + "learning_rate": 3.788761257970745e-05, + "loss": 3.6319, + "step": 739840 + }, + { + "epoch": 1.02, + "learning_rate": 3.787922663219693e-05, + "loss": 3.6346, + "step": 740352 + }, + { + "epoch": 1.02, + "learning_rate": 3.787084068468641e-05, + "loss": 3.6271, + "step": 740864 + }, + { + "epoch": 1.02, + "learning_rate": 3.786247111597962e-05, + "loss": 3.6304, + "step": 741376 + }, + { + "epoch": 1.02, + "learning_rate": 3.78540851684691e-05, + "loss": 3.6416, + "step": 741888 + }, + { + "epoch": 1.02, + "learning_rate": 3.784569922095858e-05, + "loss": 3.6371, + "step": 742400 + }, + { + "epoch": 1.02, + "learning_rate": 3.783731327344806e-05, + "loss": 3.6276, + "step": 742912 + }, + { + "epoch": 1.02, + "learning_rate": 3.782894370474127e-05, + "loss": 3.6309, + "step": 743424 + }, + { + "epoch": 1.02, + "learning_rate": 3.782055775723075e-05, + "loss": 3.622, + "step": 743936 + }, + { + "epoch": 1.02, + "learning_rate": 3.781217180972023e-05, + "loss": 3.6412, + "step": 744448 + }, + { + "epoch": 1.02, + "learning_rate": 3.780378586220971e-05, + "loss": 3.63, + "step": 744960 + }, + { + "epoch": 1.02, + "learning_rate": 3.7795416293502925e-05, + "loss": 3.6494, + "step": 745472 + }, + { + "epoch": 1.02, + "learning_rate": 3.7787030345992404e-05, + "loss": 3.6438, + "step": 745984 + }, + { + "epoch": 1.02, + "learning_rate": 3.7778644398481884e-05, + "loss": 3.6475, + "step": 746496 + }, + { + "epoch": 1.02, + "learning_rate": 3.7770258450971364e-05, + "loss": 3.6317, + "step": 747008 + }, + { + "epoch": 1.02, + "learning_rate": 3.7761888882264573e-05, + "loss": 3.6291, + "step": 747520 + }, + { + "epoch": 1.02, + "learning_rate": 3.7753502934754053e-05, + "loss": 3.6404, + "step": 748032 + }, + { + "epoch": 1.02, + "learning_rate": 3.7745116987243533e-05, + "loss": 3.639, + "step": 748544 + }, + { + "epoch": 1.02, + "learning_rate": 3.773673103973301e-05, + "loss": 3.6275, + "step": 749056 + }, + { + "epoch": 1.02, + "learning_rate": 3.772834509222249e-05, + "loss": 3.6274, + "step": 749568 + }, + { + "epoch": 1.02, + "learning_rate": 3.77199755235157e-05, + "loss": 3.639, + "step": 750080 + }, + { + "epoch": 1.02, + "learning_rate": 3.771158957600518e-05, + "loss": 3.6308, + "step": 750592 + }, + { + "epoch": 1.02, + "learning_rate": 3.770320362849466e-05, + "loss": 3.6334, + "step": 751104 + }, + { + "epoch": 1.02, + "learning_rate": 3.769483405978788e-05, + "loss": 3.6286, + "step": 751616 + }, + { + "epoch": 1.02, + "learning_rate": 3.768644811227736e-05, + "loss": 3.6346, + "step": 752128 + }, + { + "epoch": 1.02, + "learning_rate": 3.767806216476684e-05, + "loss": 3.6266, + "step": 752640 + }, + { + "epoch": 1.02, + "learning_rate": 3.766967621725632e-05, + "loss": 3.6394, + "step": 753152 + }, + { + "epoch": 1.02, + "learning_rate": 3.766130664854953e-05, + "loss": 3.6367, + "step": 753664 + }, + { + "epoch": 1.02, + "learning_rate": 3.765292070103901e-05, + "loss": 3.6495, + "step": 754176 + }, + { + "epoch": 1.02, + "learning_rate": 3.764453475352849e-05, + "loss": 3.6238, + "step": 754688 + }, + { + "epoch": 1.02, + "learning_rate": 3.763614880601797e-05, + "loss": 3.6409, + "step": 755200 + }, + { + "epoch": 1.02, + "learning_rate": 3.7627779237311176e-05, + "loss": 3.6311, + "step": 755712 + }, + { + "epoch": 1.02, + "learning_rate": 3.7619393289800656e-05, + "loss": 3.6414, + "step": 756224 + }, + { + "epoch": 1.02, + "learning_rate": 3.7611007342290136e-05, + "loss": 3.6361, + "step": 756736 + }, + { + "epoch": 1.02, + "learning_rate": 3.7602621394779616e-05, + "loss": 3.6309, + "step": 757248 + }, + { + "epoch": 1.02, + "learning_rate": 3.759425182607283e-05, + "loss": 3.6363, + "step": 757760 + }, + { + "epoch": 1.02, + "learning_rate": 3.758586587856231e-05, + "loss": 3.6518, + "step": 758272 + }, + { + "epoch": 1.02, + "learning_rate": 3.757747993105179e-05, + "loss": 3.623, + "step": 758784 + }, + { + "epoch": 1.02, + "learning_rate": 3.756909398354127e-05, + "loss": 3.6393, + "step": 759296 + }, + { + "epoch": 1.02, + "learning_rate": 3.756072441483448e-05, + "loss": 3.6348, + "step": 759808 + }, + { + "epoch": 1.02, + "learning_rate": 3.755233846732396e-05, + "loss": 3.6329, + "step": 760320 + }, + { + "epoch": 1.02, + "learning_rate": 3.754395251981344e-05, + "loss": 3.6267, + "step": 760832 + }, + { + "epoch": 1.02, + "learning_rate": 3.753556657230292e-05, + "loss": 3.6336, + "step": 761344 + }, + { + "epoch": 1.02, + "learning_rate": 3.752719700359613e-05, + "loss": 3.6376, + "step": 761856 + }, + { + "epoch": 1.02, + "learning_rate": 3.751881105608561e-05, + "loss": 3.6295, + "step": 762368 + }, + { + "epoch": 1.02, + "learning_rate": 3.751042510857509e-05, + "loss": 3.635, + "step": 762880 + }, + { + "epoch": 1.03, + "eval_loss": 3.8439929485321045, + "eval_runtime": 310.3463, + "eval_samples_per_second": 1229.565, + "eval_steps_per_second": 38.425, + "step": 763200 + }, + { + "epoch": 0.0, + "learning_rate": 3.750203916106457e-05, + "loss": 3.6269, + "step": 763392 + }, + { + "epoch": 0.0, + "learning_rate": 3.7493653213554056e-05, + "loss": 3.6231, + "step": 763904 + }, + { + "epoch": 0.0, + "learning_rate": 3.7485267266043536e-05, + "loss": 3.6276, + "step": 764416 + }, + { + "epoch": 0.0, + "learning_rate": 3.7476881318533016e-05, + "loss": 3.6366, + "step": 764928 + }, + { + "epoch": 0.0, + "learning_rate": 3.7468511749826225e-05, + "loss": 3.647, + "step": 765440 + }, + { + "epoch": 0.0, + "learning_rate": 3.7460125802315705e-05, + "loss": 3.6303, + "step": 765952 + }, + { + "epoch": 0.0, + "learning_rate": 3.7451739854805185e-05, + "loss": 3.6294, + "step": 766464 + }, + { + "epoch": 0.0, + "learning_rate": 3.7443353907294665e-05, + "loss": 3.627, + "step": 766976 + }, + { + "epoch": 0.0, + "learning_rate": 3.7434984338587874e-05, + "loss": 3.6216, + "step": 767488 + }, + { + "epoch": 0.0, + "learning_rate": 3.7426598391077354e-05, + "loss": 3.6382, + "step": 768000 + }, + { + "epoch": 0.0, + "learning_rate": 3.7418212443566834e-05, + "loss": 3.6265, + "step": 768512 + }, + { + "epoch": 0.0, + "learning_rate": 3.7409826496056314e-05, + "loss": 3.6341, + "step": 769024 + }, + { + "epoch": 0.0, + "learning_rate": 3.740145692734952e-05, + "loss": 3.6338, + "step": 769536 + }, + { + "epoch": 0.0, + "learning_rate": 3.7393070979839e-05, + "loss": 3.6205, + "step": 770048 + }, + { + "epoch": 0.0, + "learning_rate": 3.738468503232849e-05, + "loss": 3.6226, + "step": 770560 + }, + { + "epoch": 0.0, + "learning_rate": 3.737629908481796e-05, + "loss": 3.6194, + "step": 771072 + }, + { + "epoch": 0.0, + "learning_rate": 3.736792951611118e-05, + "loss": 3.6227, + "step": 771584 + }, + { + "epoch": 0.0, + "learning_rate": 3.735954356860066e-05, + "loss": 3.6237, + "step": 772096 + }, + { + "epoch": 0.0, + "learning_rate": 3.735115762109014e-05, + "loss": 3.6239, + "step": 772608 + }, + { + "epoch": 0.0, + "learning_rate": 3.734277167357961e-05, + "loss": 3.6337, + "step": 773120 + }, + { + "epoch": 0.0, + "learning_rate": 3.733440210487283e-05, + "loss": 3.6313, + "step": 773632 + }, + { + "epoch": 0.0, + "learning_rate": 3.732601615736231e-05, + "loss": 3.6358, + "step": 774144 + }, + { + "epoch": 0.0, + "learning_rate": 3.731763020985179e-05, + "loss": 3.6264, + "step": 774656 + }, + { + "epoch": 0.0, + "learning_rate": 3.730924426234126e-05, + "loss": 3.6225, + "step": 775168 + }, + { + "epoch": 0.0, + "learning_rate": 3.730087469363448e-05, + "loss": 3.6266, + "step": 775680 + }, + { + "epoch": 0.0, + "learning_rate": 3.729248874612396e-05, + "loss": 3.6334, + "step": 776192 + }, + { + "epoch": 0.0, + "learning_rate": 3.728410279861344e-05, + "loss": 3.6216, + "step": 776704 + }, + { + "epoch": 0.0, + "learning_rate": 3.727571685110292e-05, + "loss": 3.6246, + "step": 777216 + }, + { + "epoch": 0.0, + "learning_rate": 3.726734728239613e-05, + "loss": 3.6178, + "step": 777728 + }, + { + "epoch": 0.0, + "learning_rate": 3.725896133488561e-05, + "loss": 3.6155, + "step": 778240 + }, + { + "epoch": 0.01, + "learning_rate": 3.7250575387375086e-05, + "loss": 3.6176, + "step": 778752 + }, + { + "epoch": 0.01, + "learning_rate": 3.7242189439864566e-05, + "loss": 3.6296, + "step": 779264 + }, + { + "epoch": 0.01, + "learning_rate": 3.723381987115778e-05, + "loss": 3.6358, + "step": 779776 + }, + { + "epoch": 0.01, + "learning_rate": 3.722543392364726e-05, + "loss": 3.6276, + "step": 780288 + }, + { + "epoch": 0.01, + "learning_rate": 3.7217047976136735e-05, + "loss": 3.6252, + "step": 780800 + }, + { + "epoch": 0.01, + "learning_rate": 3.7208662028626215e-05, + "loss": 3.6207, + "step": 781312 + }, + { + "epoch": 0.01, + "learning_rate": 3.720029245991943e-05, + "loss": 3.6384, + "step": 781824 + }, + { + "epoch": 0.01, + "learning_rate": 3.719190651240891e-05, + "loss": 3.6189, + "step": 782336 + }, + { + "epoch": 0.01, + "learning_rate": 3.718352056489839e-05, + "loss": 3.6165, + "step": 782848 + }, + { + "epoch": 0.01, + "learning_rate": 3.717513461738787e-05, + "loss": 3.6134, + "step": 783360 + }, + { + "epoch": 0.01, + "learning_rate": 3.7166765048681086e-05, + "loss": 3.6226, + "step": 783872 + }, + { + "epoch": 0.01, + "learning_rate": 3.715837910117056e-05, + "loss": 3.6217, + "step": 784384 + }, + { + "epoch": 0.01, + "learning_rate": 3.714999315366004e-05, + "loss": 3.6234, + "step": 784896 + }, + { + "epoch": 0.01, + "learning_rate": 3.714160720614952e-05, + "loss": 3.6203, + "step": 785408 + }, + { + "epoch": 0.01, + "learning_rate": 3.7133237637442735e-05, + "loss": 3.627, + "step": 785920 + }, + { + "epoch": 0.01, + "learning_rate": 3.712485168993221e-05, + "loss": 3.6188, + "step": 786432 + }, + { + "epoch": 0.01, + "learning_rate": 3.711646574242169e-05, + "loss": 3.6184, + "step": 786944 + }, + { + "epoch": 0.01, + "learning_rate": 3.710807979491117e-05, + "loss": 3.6156, + "step": 787456 + }, + { + "epoch": 0.01, + "learning_rate": 3.7099710226204384e-05, + "loss": 3.5961, + "step": 787968 + }, + { + "epoch": 0.01, + "learning_rate": 3.7091324278693864e-05, + "loss": 3.6337, + "step": 788480 + }, + { + "epoch": 0.01, + "learning_rate": 3.7082938331183344e-05, + "loss": 3.6151, + "step": 788992 + }, + { + "epoch": 0.01, + "learning_rate": 3.7074552383672824e-05, + "loss": 3.6279, + "step": 789504 + }, + { + "epoch": 0.01, + "learning_rate": 3.706618281496603e-05, + "loss": 3.6156, + "step": 790016 + }, + { + "epoch": 0.01, + "learning_rate": 3.705779686745551e-05, + "loss": 3.6146, + "step": 790528 + }, + { + "epoch": 0.01, + "learning_rate": 3.704941091994499e-05, + "loss": 3.605, + "step": 791040 + }, + { + "epoch": 0.01, + "learning_rate": 3.704102497243447e-05, + "loss": 3.6181, + "step": 791552 + }, + { + "epoch": 0.01, + "learning_rate": 3.703265540372768e-05, + "loss": 3.6157, + "step": 792064 + }, + { + "epoch": 0.01, + "learning_rate": 3.702426945621716e-05, + "loss": 3.6105, + "step": 792576 + }, + { + "epoch": 0.01, + "learning_rate": 3.701588350870664e-05, + "loss": 3.6308, + "step": 793088 + }, + { + "epoch": 0.01, + "learning_rate": 3.700749756119612e-05, + "loss": 3.6154, + "step": 793600 + }, + { + "epoch": 0.01, + "learning_rate": 3.699912799248934e-05, + "loss": 3.6035, + "step": 794112 + }, + { + "epoch": 0.01, + "learning_rate": 3.699074204497882e-05, + "loss": 3.6247, + "step": 794624 + }, + { + "epoch": 0.01, + "learning_rate": 3.69823560974683e-05, + "loss": 3.6124, + "step": 795136 + }, + { + "epoch": 0.01, + "learning_rate": 3.697397014995778e-05, + "loss": 3.6102, + "step": 795648 + }, + { + "epoch": 0.01, + "learning_rate": 3.696560058125099e-05, + "loss": 3.6228, + "step": 796160 + }, + { + "epoch": 0.01, + "learning_rate": 3.695721463374047e-05, + "loss": 3.6157, + "step": 796672 + }, + { + "epoch": 0.01, + "learning_rate": 3.694882868622995e-05, + "loss": 3.6084, + "step": 797184 + }, + { + "epoch": 0.01, + "learning_rate": 3.694044273871943e-05, + "loss": 3.6187, + "step": 797696 + }, + { + "epoch": 0.01, + "learning_rate": 3.6932073170012636e-05, + "loss": 3.6052, + "step": 798208 + }, + { + "epoch": 0.01, + "learning_rate": 3.6923687222502116e-05, + "loss": 3.6087, + "step": 798720 + }, + { + "epoch": 0.01, + "learning_rate": 3.6915301274991596e-05, + "loss": 3.6224, + "step": 799232 + }, + { + "epoch": 0.01, + "learning_rate": 3.6906915327481076e-05, + "loss": 3.6201, + "step": 799744 + }, + { + "epoch": 0.01, + "learning_rate": 3.689854575877429e-05, + "loss": 3.6248, + "step": 800256 + }, + { + "epoch": 0.01, + "learning_rate": 3.689015981126377e-05, + "loss": 3.6164, + "step": 800768 + }, + { + "epoch": 0.01, + "learning_rate": 3.688177386375325e-05, + "loss": 3.638, + "step": 801280 + }, + { + "epoch": 0.01, + "learning_rate": 3.687340429504646e-05, + "loss": 3.6119, + "step": 801792 + }, + { + "epoch": 0.01, + "learning_rate": 3.686501834753594e-05, + "loss": 3.6262, + "step": 802304 + }, + { + "epoch": 0.01, + "learning_rate": 3.685663240002542e-05, + "loss": 3.6162, + "step": 802816 + }, + { + "epoch": 0.01, + "learning_rate": 3.68482464525149e-05, + "loss": 3.6132, + "step": 803328 + }, + { + "epoch": 0.01, + "learning_rate": 3.683987688380811e-05, + "loss": 3.6143, + "step": 803840 + }, + { + "epoch": 0.01, + "learning_rate": 3.683149093629759e-05, + "loss": 3.6286, + "step": 804352 + }, + { + "epoch": 0.01, + "learning_rate": 3.682310498878707e-05, + "loss": 3.6179, + "step": 804864 + }, + { + "epoch": 0.01, + "learning_rate": 3.681471904127655e-05, + "loss": 3.6304, + "step": 805376 + }, + { + "epoch": 0.01, + "learning_rate": 3.680633309376603e-05, + "loss": 3.6037, + "step": 805888 + }, + { + "epoch": 0.01, + "learning_rate": 3.679794714625551e-05, + "loss": 3.6031, + "step": 806400 + }, + { + "epoch": 0.01, + "learning_rate": 3.6789561198744996e-05, + "loss": 3.6176, + "step": 806912 + }, + { + "epoch": 0.01, + "learning_rate": 3.6781175251234476e-05, + "loss": 3.6267, + "step": 807424 + }, + { + "epoch": 0.01, + "learning_rate": 3.6772805682527685e-05, + "loss": 3.6141, + "step": 807936 + }, + { + "epoch": 0.01, + "learning_rate": 3.6764419735017165e-05, + "loss": 3.6176, + "step": 808448 + }, + { + "epoch": 0.01, + "learning_rate": 3.6756033787506645e-05, + "loss": 3.6127, + "step": 808960 + }, + { + "epoch": 0.02, + "learning_rate": 3.6747647839996125e-05, + "loss": 3.6108, + "step": 809472 + }, + { + "epoch": 0.02, + "learning_rate": 3.6739278271289334e-05, + "loss": 3.6142, + "step": 809984 + }, + { + "epoch": 0.02, + "learning_rate": 3.6730892323778814e-05, + "loss": 3.6085, + "step": 810496 + }, + { + "epoch": 0.02, + "learning_rate": 3.6722506376268294e-05, + "loss": 3.623, + "step": 811008 + }, + { + "epoch": 0.02, + "learning_rate": 3.6714120428757774e-05, + "loss": 3.633, + "step": 811520 + }, + { + "epoch": 0.02, + "learning_rate": 3.670575086005098e-05, + "loss": 3.6275, + "step": 812032 + }, + { + "epoch": 0.02, + "learning_rate": 3.669736491254046e-05, + "loss": 3.6081, + "step": 812544 + }, + { + "epoch": 0.02, + "learning_rate": 3.668897896502995e-05, + "loss": 3.6082, + "step": 813056 + }, + { + "epoch": 0.02, + "learning_rate": 3.668059301751943e-05, + "loss": 3.6147, + "step": 813568 + }, + { + "epoch": 0.02, + "learning_rate": 3.667222344881264e-05, + "loss": 3.6199, + "step": 814080 + }, + { + "epoch": 0.02, + "learning_rate": 3.666383750130212e-05, + "loss": 3.6184, + "step": 814592 + }, + { + "epoch": 0.02, + "learning_rate": 3.66554515537916e-05, + "loss": 3.6215, + "step": 815104 + }, + { + "epoch": 0.02, + "learning_rate": 3.664706560628108e-05, + "loss": 3.619, + "step": 815616 + }, + { + "epoch": 0.02, + "learning_rate": 3.663869603757429e-05, + "loss": 3.6092, + "step": 816128 + }, + { + "epoch": 0.02, + "learning_rate": 3.663031009006377e-05, + "loss": 3.6125, + "step": 816640 + }, + { + "epoch": 0.02, + "learning_rate": 3.662192414255325e-05, + "loss": 3.6058, + "step": 817152 + }, + { + "epoch": 0.02, + "learning_rate": 3.661353819504273e-05, + "loss": 3.6089, + "step": 817664 + }, + { + "epoch": 0.02, + "learning_rate": 3.660516862633594e-05, + "loss": 3.6205, + "step": 818176 + }, + { + "epoch": 0.02, + "learning_rate": 3.659678267882542e-05, + "loss": 3.6148, + "step": 818688 + }, + { + "epoch": 0.02, + "learning_rate": 3.6588396731314903e-05, + "loss": 3.6053, + "step": 819200 + }, + { + "epoch": 0.02, + "learning_rate": 3.6580010783804383e-05, + "loss": 3.6107, + "step": 819712 + }, + { + "epoch": 0.02, + "learning_rate": 3.657164121509759e-05, + "loss": 3.5986, + "step": 820224 + }, + { + "epoch": 0.02, + "learning_rate": 3.656325526758707e-05, + "loss": 3.6199, + "step": 820736 + }, + { + "epoch": 0.02, + "learning_rate": 3.655486932007655e-05, + "loss": 3.6137, + "step": 821248 + }, + { + "epoch": 0.02, + "learning_rate": 3.654648337256603e-05, + "loss": 3.6223, + "step": 821760 + }, + { + "epoch": 0.02, + "learning_rate": 3.653813018266297e-05, + "loss": 3.6242, + "step": 822272 + }, + { + "epoch": 0.02, + "learning_rate": 3.652974423515245e-05, + "loss": 3.6264, + "step": 822784 + }, + { + "epoch": 0.02, + "learning_rate": 3.652135828764193e-05, + "loss": 3.611, + "step": 823296 + }, + { + "epoch": 0.02, + "learning_rate": 3.651297234013141e-05, + "loss": 3.6104, + "step": 823808 + }, + { + "epoch": 0.02, + "learning_rate": 3.650458639262089e-05, + "loss": 3.616, + "step": 824320 + }, + { + "epoch": 0.02, + "learning_rate": 3.649620044511037e-05, + "loss": 3.6177, + "step": 824832 + }, + { + "epoch": 0.02, + "learning_rate": 3.648781449759985e-05, + "loss": 3.6072, + "step": 825344 + }, + { + "epoch": 0.02, + "learning_rate": 3.647942855008934e-05, + "loss": 3.6036, + "step": 825856 + }, + { + "epoch": 0.02, + "learning_rate": 3.6471058981382546e-05, + "loss": 3.6182, + "step": 826368 + }, + { + "epoch": 0.02, + "learning_rate": 3.6462673033872026e-05, + "loss": 3.608, + "step": 826880 + }, + { + "epoch": 0.02, + "learning_rate": 3.6454287086361506e-05, + "loss": 3.6095, + "step": 827392 + }, + { + "epoch": 0.02, + "learning_rate": 3.6445901138850986e-05, + "loss": 3.6068, + "step": 827904 + }, + { + "epoch": 0.02, + "learning_rate": 3.6437531570144195e-05, + "loss": 3.6171, + "step": 828416 + }, + { + "epoch": 0.02, + "learning_rate": 3.6429145622633675e-05, + "loss": 3.6019, + "step": 828928 + }, + { + "epoch": 0.02, + "learning_rate": 3.6420759675123155e-05, + "loss": 3.6198, + "step": 829440 + }, + { + "epoch": 0.02, + "learning_rate": 3.6412373727612635e-05, + "loss": 3.6155, + "step": 829952 + }, + { + "epoch": 0.02, + "learning_rate": 3.6404004158905844e-05, + "loss": 3.6278, + "step": 830464 + }, + { + "epoch": 0.02, + "learning_rate": 3.6395618211395324e-05, + "loss": 3.5994, + "step": 830976 + }, + { + "epoch": 0.02, + "learning_rate": 3.6387232263884804e-05, + "loss": 3.6179, + "step": 831488 + }, + { + "epoch": 0.02, + "learning_rate": 3.637884631637429e-05, + "loss": 3.6181, + "step": 832000 + }, + { + "epoch": 0.02, + "learning_rate": 3.63704767476675e-05, + "loss": 3.6157, + "step": 832512 + }, + { + "epoch": 0.02, + "learning_rate": 3.636209080015698e-05, + "loss": 3.6166, + "step": 833024 + }, + { + "epoch": 0.02, + "learning_rate": 3.635370485264646e-05, + "loss": 3.6091, + "step": 833536 + }, + { + "epoch": 0.02, + "learning_rate": 3.634531890513593e-05, + "loss": 3.6114, + "step": 834048 + }, + { + "epoch": 0.02, + "learning_rate": 3.633694933642915e-05, + "loss": 3.6299, + "step": 834560 + }, + { + "epoch": 0.02, + "learning_rate": 3.632856338891863e-05, + "loss": 3.6048, + "step": 835072 + }, + { + "epoch": 0.02, + "learning_rate": 3.632017744140811e-05, + "loss": 3.6152, + "step": 835584 + }, + { + "epoch": 0.02, + "learning_rate": 3.631179149389758e-05, + "loss": 3.6141, + "step": 836096 + }, + { + "epoch": 0.02, + "learning_rate": 3.63034219251908e-05, + "loss": 3.6094, + "step": 836608 + }, + { + "epoch": 0.02, + "learning_rate": 3.629503597768028e-05, + "loss": 3.6099, + "step": 837120 + }, + { + "epoch": 0.02, + "learning_rate": 3.628665003016976e-05, + "loss": 3.6133, + "step": 837632 + }, + { + "epoch": 0.02, + "learning_rate": 3.627826408265924e-05, + "loss": 3.6168, + "step": 838144 + }, + { + "epoch": 0.02, + "learning_rate": 3.6269894513952454e-05, + "loss": 3.6132, + "step": 838656 + }, + { + "epoch": 0.02, + "learning_rate": 3.6261508566441933e-05, + "loss": 3.6089, + "step": 839168 + }, + { + "epoch": 0.03, + "eval_loss": 3.8413844108581543, + "eval_runtime": 311.9356, + "eval_samples_per_second": 1223.3, + "eval_steps_per_second": 38.229, + "step": 839520 + }, + { + "epoch": 1.0, + "learning_rate": 3.625312261893141e-05, + "loss": 3.607, + "step": 839680 + }, + { + "epoch": 1.0, + "learning_rate": 3.6244736671420887e-05, + "loss": 3.5995, + "step": 840192 + }, + { + "epoch": 1.0, + "learning_rate": 3.62363671027141e-05, + "loss": 3.608, + "step": 840704 + }, + { + "epoch": 1.0, + "learning_rate": 3.622798115520358e-05, + "loss": 3.6159, + "step": 841216 + }, + { + "epoch": 1.0, + "learning_rate": 3.6219595207693056e-05, + "loss": 3.6223, + "step": 841728 + }, + { + "epoch": 1.0, + "learning_rate": 3.621122563898627e-05, + "loss": 3.6101, + "step": 842240 + }, + { + "epoch": 1.0, + "learning_rate": 3.620283969147575e-05, + "loss": 3.6091, + "step": 842752 + }, + { + "epoch": 1.0, + "learning_rate": 3.619445374396523e-05, + "loss": 3.6079, + "step": 843264 + }, + { + "epoch": 1.0, + "learning_rate": 3.618606779645471e-05, + "loss": 3.5986, + "step": 843776 + }, + { + "epoch": 1.0, + "learning_rate": 3.617769822774793e-05, + "loss": 3.6152, + "step": 844288 + }, + { + "epoch": 1.0, + "learning_rate": 3.616931228023741e-05, + "loss": 3.6072, + "step": 844800 + }, + { + "epoch": 1.0, + "learning_rate": 3.616092633272688e-05, + "loss": 3.614, + "step": 845312 + }, + { + "epoch": 1.0, + "learning_rate": 3.615254038521636e-05, + "loss": 3.6118, + "step": 845824 + }, + { + "epoch": 1.0, + "learning_rate": 3.6144170816509576e-05, + "loss": 3.5973, + "step": 846336 + }, + { + "epoch": 1.0, + "learning_rate": 3.6135784868999056e-05, + "loss": 3.6016, + "step": 846848 + }, + { + "epoch": 1.0, + "learning_rate": 3.612739892148853e-05, + "loss": 3.5952, + "step": 847360 + }, + { + "epoch": 1.0, + "learning_rate": 3.611901297397801e-05, + "loss": 3.6072, + "step": 847872 + }, + { + "epoch": 1.0, + "learning_rate": 3.6110643405271225e-05, + "loss": 3.6037, + "step": 848384 + }, + { + "epoch": 1.0, + "learning_rate": 3.6102257457760705e-05, + "loss": 3.6011, + "step": 848896 + }, + { + "epoch": 1.0, + "learning_rate": 3.6093871510250185e-05, + "loss": 3.6094, + "step": 849408 + }, + { + "epoch": 1.0, + "learning_rate": 3.6085485562739665e-05, + "loss": 3.611, + "step": 849920 + }, + { + "epoch": 1.0, + "learning_rate": 3.607711599403288e-05, + "loss": 3.6156, + "step": 850432 + }, + { + "epoch": 1.0, + "learning_rate": 3.6068730046522354e-05, + "loss": 3.6073, + "step": 850944 + }, + { + "epoch": 1.0, + "learning_rate": 3.6060344099011834e-05, + "loss": 3.6049, + "step": 851456 + }, + { + "epoch": 1.0, + "learning_rate": 3.6051958151501314e-05, + "loss": 3.6062, + "step": 851968 + }, + { + "epoch": 1.0, + "learning_rate": 3.604358858279453e-05, + "loss": 3.6109, + "step": 852480 + }, + { + "epoch": 1.0, + "learning_rate": 3.6035202635284e-05, + "loss": 3.6002, + "step": 852992 + }, + { + "epoch": 1.0, + "learning_rate": 3.602681668777348e-05, + "loss": 3.6049, + "step": 853504 + }, + { + "epoch": 1.0, + "learning_rate": 3.601843074026296e-05, + "loss": 3.5994, + "step": 854016 + }, + { + "epoch": 1.0, + "learning_rate": 3.601006117155617e-05, + "loss": 3.595, + "step": 854528 + }, + { + "epoch": 1.01, + "learning_rate": 3.600167522404566e-05, + "loss": 3.5989, + "step": 855040 + }, + { + "epoch": 1.01, + "learning_rate": 3.599328927653514e-05, + "loss": 3.6066, + "step": 855552 + }, + { + "epoch": 1.01, + "learning_rate": 3.598490332902462e-05, + "loss": 3.6075, + "step": 856064 + }, + { + "epoch": 1.01, + "learning_rate": 3.597653376031783e-05, + "loss": 3.6169, + "step": 856576 + }, + { + "epoch": 1.01, + "learning_rate": 3.596814781280731e-05, + "loss": 3.6002, + "step": 857088 + }, + { + "epoch": 1.01, + "learning_rate": 3.595976186529679e-05, + "loss": 3.6051, + "step": 857600 + }, + { + "epoch": 1.01, + "learning_rate": 3.595137591778627e-05, + "loss": 3.6178, + "step": 858112 + }, + { + "epoch": 1.01, + "learning_rate": 3.594300634907948e-05, + "loss": 3.5949, + "step": 858624 + }, + { + "epoch": 1.01, + "learning_rate": 3.593462040156896e-05, + "loss": 3.5967, + "step": 859136 + }, + { + "epoch": 1.01, + "learning_rate": 3.592623445405844e-05, + "loss": 3.5941, + "step": 859648 + }, + { + "epoch": 1.01, + "learning_rate": 3.591784850654792e-05, + "loss": 3.6009, + "step": 860160 + }, + { + "epoch": 1.01, + "learning_rate": 3.5909478937841126e-05, + "loss": 3.6013, + "step": 860672 + }, + { + "epoch": 1.01, + "learning_rate": 3.590109299033061e-05, + "loss": 3.6007, + "step": 861184 + }, + { + "epoch": 1.01, + "learning_rate": 3.589270704282009e-05, + "loss": 3.6034, + "step": 861696 + }, + { + "epoch": 1.01, + "learning_rate": 3.588432109530957e-05, + "loss": 3.603, + "step": 862208 + }, + { + "epoch": 1.01, + "learning_rate": 3.587595152660278e-05, + "loss": 3.6064, + "step": 862720 + }, + { + "epoch": 1.01, + "learning_rate": 3.586756557909226e-05, + "loss": 3.5936, + "step": 863232 + }, + { + "epoch": 1.01, + "learning_rate": 3.585917963158174e-05, + "loss": 3.5964, + "step": 863744 + }, + { + "epoch": 1.01, + "learning_rate": 3.585079368407122e-05, + "loss": 3.5732, + "step": 864256 + }, + { + "epoch": 1.01, + "learning_rate": 3.584242411536443e-05, + "loss": 3.6113, + "step": 864768 + }, + { + "epoch": 1.01, + "learning_rate": 3.583403816785391e-05, + "loss": 3.5967, + "step": 865280 + }, + { + "epoch": 1.01, + "learning_rate": 3.582565222034339e-05, + "loss": 3.6047, + "step": 865792 + }, + { + "epoch": 1.01, + "learning_rate": 3.581726627283287e-05, + "loss": 3.5987, + "step": 866304 + }, + { + "epoch": 1.01, + "learning_rate": 3.580889670412608e-05, + "loss": 3.5944, + "step": 866816 + }, + { + "epoch": 1.01, + "learning_rate": 3.5800510756615566e-05, + "loss": 3.5844, + "step": 867328 + }, + { + "epoch": 1.01, + "learning_rate": 3.5792124809105046e-05, + "loss": 3.5975, + "step": 867840 + }, + { + "epoch": 1.01, + "learning_rate": 3.5783738861594526e-05, + "loss": 3.5993, + "step": 868352 + }, + { + "epoch": 1.01, + "learning_rate": 3.5775369292887735e-05, + "loss": 3.5887, + "step": 868864 + }, + { + "epoch": 1.01, + "learning_rate": 3.5766983345377215e-05, + "loss": 3.6105, + "step": 869376 + }, + { + "epoch": 1.01, + "learning_rate": 3.5758597397866695e-05, + "loss": 3.5989, + "step": 869888 + }, + { + "epoch": 1.01, + "learning_rate": 3.5750211450356175e-05, + "loss": 3.5779, + "step": 870400 + }, + { + "epoch": 1.01, + "learning_rate": 3.5741841881649384e-05, + "loss": 3.6061, + "step": 870912 + }, + { + "epoch": 1.01, + "learning_rate": 3.5733455934138864e-05, + "loss": 3.5959, + "step": 871424 + }, + { + "epoch": 1.01, + "learning_rate": 3.5725069986628344e-05, + "loss": 3.5904, + "step": 871936 + }, + { + "epoch": 1.01, + "learning_rate": 3.5716684039117824e-05, + "loss": 3.5995, + "step": 872448 + }, + { + "epoch": 1.01, + "learning_rate": 3.570831447041103e-05, + "loss": 3.5959, + "step": 872960 + }, + { + "epoch": 1.01, + "learning_rate": 3.569992852290052e-05, + "loss": 3.5867, + "step": 873472 + }, + { + "epoch": 1.01, + "learning_rate": 3.569154257539e-05, + "loss": 3.6009, + "step": 873984 + }, + { + "epoch": 1.01, + "learning_rate": 3.568317300668321e-05, + "loss": 3.5846, + "step": 874496 + }, + { + "epoch": 1.01, + "learning_rate": 3.567478705917269e-05, + "loss": 3.586, + "step": 875008 + }, + { + "epoch": 1.01, + "learning_rate": 3.566640111166217e-05, + "loss": 3.6052, + "step": 875520 + }, + { + "epoch": 1.01, + "learning_rate": 3.565801516415165e-05, + "loss": 3.5969, + "step": 876032 + }, + { + "epoch": 1.01, + "learning_rate": 3.564964559544486e-05, + "loss": 3.6059, + "step": 876544 + }, + { + "epoch": 1.01, + "learning_rate": 3.564125964793434e-05, + "loss": 3.6, + "step": 877056 + }, + { + "epoch": 1.01, + "learning_rate": 3.563287370042382e-05, + "loss": 3.6113, + "step": 877568 + }, + { + "epoch": 1.01, + "learning_rate": 3.56244877529133e-05, + "loss": 3.5942, + "step": 878080 + }, + { + "epoch": 1.01, + "learning_rate": 3.561611818420651e-05, + "loss": 3.6091, + "step": 878592 + }, + { + "epoch": 1.01, + "learning_rate": 3.560773223669599e-05, + "loss": 3.5931, + "step": 879104 + }, + { + "epoch": 1.01, + "learning_rate": 3.5599346289185473e-05, + "loss": 3.5958, + "step": 879616 + }, + { + "epoch": 1.01, + "learning_rate": 3.5590960341674953e-05, + "loss": 3.5956, + "step": 880128 + }, + { + "epoch": 1.01, + "learning_rate": 3.558259077296816e-05, + "loss": 3.6052, + "step": 880640 + }, + { + "epoch": 1.01, + "learning_rate": 3.557420482545764e-05, + "loss": 3.6024, + "step": 881152 + }, + { + "epoch": 1.01, + "learning_rate": 3.556581887794712e-05, + "loss": 3.6111, + "step": 881664 + }, + { + "epoch": 1.01, + "learning_rate": 3.55574329304366e-05, + "loss": 3.5833, + "step": 882176 + }, + { + "epoch": 1.01, + "learning_rate": 3.554906336172981e-05, + "loss": 3.5835, + "step": 882688 + }, + { + "epoch": 1.01, + "learning_rate": 3.554067741421929e-05, + "loss": 3.5976, + "step": 883200 + }, + { + "epoch": 1.01, + "learning_rate": 3.553229146670877e-05, + "loss": 3.6068, + "step": 883712 + }, + { + "epoch": 1.01, + "learning_rate": 3.552390551919825e-05, + "loss": 3.5929, + "step": 884224 + }, + { + "epoch": 1.01, + "learning_rate": 3.551553595049146e-05, + "loss": 3.6015, + "step": 884736 + }, + { + "epoch": 1.01, + "learning_rate": 3.550715000298094e-05, + "loss": 3.5932, + "step": 885248 + }, + { + "epoch": 1.02, + "learning_rate": 3.549876405547042e-05, + "loss": 3.5867, + "step": 885760 + }, + { + "epoch": 1.02, + "learning_rate": 3.549037810795991e-05, + "loss": 3.5927, + "step": 886272 + }, + { + "epoch": 1.02, + "learning_rate": 3.548199216044939e-05, + "loss": 3.5895, + "step": 886784 + }, + { + "epoch": 1.02, + "learning_rate": 3.5473622591742596e-05, + "loss": 3.6033, + "step": 887296 + }, + { + "epoch": 1.02, + "learning_rate": 3.5465236644232076e-05, + "loss": 3.61, + "step": 887808 + }, + { + "epoch": 1.02, + "learning_rate": 3.5456850696721556e-05, + "loss": 3.6111, + "step": 888320 + }, + { + "epoch": 1.02, + "learning_rate": 3.5448481128014765e-05, + "loss": 3.5853, + "step": 888832 + }, + { + "epoch": 1.02, + "learning_rate": 3.5440095180504245e-05, + "loss": 3.5923, + "step": 889344 + }, + { + "epoch": 1.02, + "learning_rate": 3.5431709232993725e-05, + "loss": 3.5952, + "step": 889856 + }, + { + "epoch": 1.02, + "learning_rate": 3.5423323285483205e-05, + "loss": 3.6026, + "step": 890368 + }, + { + "epoch": 1.02, + "learning_rate": 3.5414953716776414e-05, + "loss": 3.5958, + "step": 890880 + }, + { + "epoch": 1.02, + "learning_rate": 3.5406567769265894e-05, + "loss": 3.6028, + "step": 891392 + }, + { + "epoch": 1.02, + "learning_rate": 3.5398181821755374e-05, + "loss": 3.5969, + "step": 891904 + }, + { + "epoch": 1.02, + "learning_rate": 3.538979587424486e-05, + "loss": 3.5905, + "step": 892416 + }, + { + "epoch": 1.02, + "learning_rate": 3.538142630553807e-05, + "loss": 3.5935, + "step": 892928 + }, + { + "epoch": 1.02, + "learning_rate": 3.537304035802755e-05, + "loss": 3.586, + "step": 893440 + }, + { + "epoch": 1.02, + "learning_rate": 3.536465441051703e-05, + "loss": 3.5906, + "step": 893952 + }, + { + "epoch": 1.02, + "learning_rate": 3.535626846300651e-05, + "loss": 3.5987, + "step": 894464 + }, + { + "epoch": 1.02, + "learning_rate": 3.534789889429972e-05, + "loss": 3.5984, + "step": 894976 + }, + { + "epoch": 1.02, + "learning_rate": 3.53395129467892e-05, + "loss": 3.5841, + "step": 895488 + }, + { + "epoch": 1.02, + "learning_rate": 3.533112699927868e-05, + "loss": 3.5926, + "step": 896000 + }, + { + "epoch": 1.02, + "learning_rate": 3.532274105176816e-05, + "loss": 3.5766, + "step": 896512 + }, + { + "epoch": 1.02, + "learning_rate": 3.531437148306137e-05, + "loss": 3.605, + "step": 897024 + }, + { + "epoch": 1.02, + "learning_rate": 3.530598553555085e-05, + "loss": 3.5917, + "step": 897536 + }, + { + "epoch": 1.02, + "learning_rate": 3.529759958804033e-05, + "loss": 3.6031, + "step": 898048 + }, + { + "epoch": 1.02, + "learning_rate": 3.5289213640529814e-05, + "loss": 3.6035, + "step": 898560 + }, + { + "epoch": 1.02, + "learning_rate": 3.5280844071823024e-05, + "loss": 3.6059, + "step": 899072 + }, + { + "epoch": 1.02, + "learning_rate": 3.5272458124312503e-05, + "loss": 3.5941, + "step": 899584 + }, + { + "epoch": 1.02, + "learning_rate": 3.5264072176801983e-05, + "loss": 3.5891, + "step": 900096 + }, + { + "epoch": 1.02, + "learning_rate": 3.525568622929146e-05, + "loss": 3.5985, + "step": 900608 + }, + { + "epoch": 1.02, + "learning_rate": 3.524731666058467e-05, + "loss": 3.5957, + "step": 901120 + }, + { + "epoch": 1.02, + "learning_rate": 3.523893071307415e-05, + "loss": 3.591, + "step": 901632 + }, + { + "epoch": 1.02, + "learning_rate": 3.523054476556363e-05, + "loss": 3.5851, + "step": 902144 + }, + { + "epoch": 1.02, + "learning_rate": 3.522215881805311e-05, + "loss": 3.5942, + "step": 902656 + }, + { + "epoch": 1.02, + "learning_rate": 3.521378924934632e-05, + "loss": 3.5897, + "step": 903168 + }, + { + "epoch": 1.02, + "learning_rate": 3.52054033018358e-05, + "loss": 3.5917, + "step": 903680 + }, + { + "epoch": 1.02, + "learning_rate": 3.519701735432528e-05, + "loss": 3.5868, + "step": 904192 + }, + { + "epoch": 1.02, + "learning_rate": 3.518863140681477e-05, + "loss": 3.5956, + "step": 904704 + }, + { + "epoch": 1.02, + "learning_rate": 3.518026183810798e-05, + "loss": 3.5819, + "step": 905216 + }, + { + "epoch": 1.02, + "learning_rate": 3.517187589059746e-05, + "loss": 3.6015, + "step": 905728 + }, + { + "epoch": 1.02, + "learning_rate": 3.516348994308694e-05, + "loss": 3.5923, + "step": 906240 + }, + { + "epoch": 1.02, + "learning_rate": 3.515510399557642e-05, + "loss": 3.6095, + "step": 906752 + }, + { + "epoch": 1.02, + "learning_rate": 3.5146734426869626e-05, + "loss": 3.5836, + "step": 907264 + }, + { + "epoch": 1.02, + "learning_rate": 3.5138348479359106e-05, + "loss": 3.5971, + "step": 907776 + }, + { + "epoch": 1.02, + "learning_rate": 3.5129962531848586e-05, + "loss": 3.5937, + "step": 908288 + }, + { + "epoch": 1.02, + "learning_rate": 3.5121576584338066e-05, + "loss": 3.5968, + "step": 908800 + }, + { + "epoch": 1.02, + "learning_rate": 3.5113207015631275e-05, + "loss": 3.5976, + "step": 909312 + }, + { + "epoch": 1.02, + "learning_rate": 3.5104821068120755e-05, + "loss": 3.5901, + "step": 909824 + }, + { + "epoch": 1.02, + "learning_rate": 3.5096435120610235e-05, + "loss": 3.5949, + "step": 910336 + }, + { + "epoch": 1.02, + "learning_rate": 3.508804917309972e-05, + "loss": 3.6071, + "step": 910848 + }, + { + "epoch": 1.02, + "learning_rate": 3.507967960439293e-05, + "loss": 3.5903, + "step": 911360 + }, + { + "epoch": 1.02, + "learning_rate": 3.507129365688241e-05, + "loss": 3.5955, + "step": 911872 + }, + { + "epoch": 1.02, + "learning_rate": 3.506290770937189e-05, + "loss": 3.5946, + "step": 912384 + }, + { + "epoch": 1.02, + "learning_rate": 3.505452176186137e-05, + "loss": 3.5918, + "step": 912896 + }, + { + "epoch": 1.02, + "learning_rate": 3.504615219315458e-05, + "loss": 3.591, + "step": 913408 + }, + { + "epoch": 1.02, + "learning_rate": 3.503776624564406e-05, + "loss": 3.5924, + "step": 913920 + }, + { + "epoch": 1.02, + "learning_rate": 3.502938029813354e-05, + "loss": 3.5947, + "step": 914432 + }, + { + "epoch": 1.02, + "learning_rate": 3.502099435062302e-05, + "loss": 3.5938, + "step": 914944 + }, + { + "epoch": 1.02, + "learning_rate": 3.501262478191623e-05, + "loss": 3.5858, + "step": 915456 + }, + { + "epoch": 1.03, + "eval_loss": 3.840613603591919, + "eval_runtime": 304.6263, + "eval_samples_per_second": 1252.653, + "eval_steps_per_second": 39.146, + "step": 915840 + }, + { + "epoch": 0.0, + "learning_rate": 3.500423883440571e-05, + "loss": 3.5967, + "step": 915968 + }, + { + "epoch": 0.0, + "learning_rate": 3.499585288689519e-05, + "loss": 3.5762, + "step": 916480 + }, + { + "epoch": 0.0, + "learning_rate": 3.4987466939384675e-05, + "loss": 3.5888, + "step": 916992 + }, + { + "epoch": 0.0, + "learning_rate": 3.497908099187415e-05, + "loss": 3.6007, + "step": 917504 + }, + { + "epoch": 0.0, + "learning_rate": 3.4970711423167364e-05, + "loss": 3.5966, + "step": 918016 + }, + { + "epoch": 0.0, + "learning_rate": 3.4962325475656844e-05, + "loss": 3.5935, + "step": 918528 + }, + { + "epoch": 0.0, + "learning_rate": 3.4953939528146324e-05, + "loss": 3.5924, + "step": 919040 + }, + { + "epoch": 0.0, + "learning_rate": 3.49455535806358e-05, + "loss": 3.5875, + "step": 919552 + }, + { + "epoch": 0.0, + "learning_rate": 3.4937184011929013e-05, + "loss": 3.5791, + "step": 920064 + }, + { + "epoch": 0.0, + "learning_rate": 3.492879806441849e-05, + "loss": 3.5888, + "step": 920576 + }, + { + "epoch": 0.0, + "learning_rate": 3.492041211690797e-05, + "loss": 3.5918, + "step": 921088 + }, + { + "epoch": 0.0, + "learning_rate": 3.4912026169397447e-05, + "loss": 3.5934, + "step": 921600 + }, + { + "epoch": 0.0, + "learning_rate": 3.490365660069066e-05, + "loss": 3.5939, + "step": 922112 + }, + { + "epoch": 0.0, + "learning_rate": 3.489527065318014e-05, + "loss": 3.577, + "step": 922624 + }, + { + "epoch": 0.0, + "learning_rate": 3.488688470566962e-05, + "loss": 3.582, + "step": 923136 + }, + { + "epoch": 0.0, + "learning_rate": 3.48784987581591e-05, + "loss": 3.5762, + "step": 923648 + }, + { + "epoch": 0.0, + "learning_rate": 3.487012918945232e-05, + "loss": 3.5869, + "step": 924160 + }, + { + "epoch": 0.0, + "learning_rate": 3.48617432419418e-05, + "loss": 3.5852, + "step": 924672 + }, + { + "epoch": 0.0, + "learning_rate": 3.485335729443127e-05, + "loss": 3.5809, + "step": 925184 + }, + { + "epoch": 0.0, + "learning_rate": 3.484497134692075e-05, + "loss": 3.5921, + "step": 925696 + }, + { + "epoch": 0.0, + "learning_rate": 3.483660177821397e-05, + "loss": 3.5926, + "step": 926208 + }, + { + "epoch": 0.0, + "learning_rate": 3.482821583070345e-05, + "loss": 3.5956, + "step": 926720 + }, + { + "epoch": 0.0, + "learning_rate": 3.481982988319292e-05, + "loss": 3.5876, + "step": 927232 + }, + { + "epoch": 0.0, + "learning_rate": 3.48114439356824e-05, + "loss": 3.5842, + "step": 927744 + }, + { + "epoch": 0.0, + "learning_rate": 3.4803074366975616e-05, + "loss": 3.5891, + "step": 928256 + }, + { + "epoch": 0.0, + "learning_rate": 3.4794688419465096e-05, + "loss": 3.591, + "step": 928768 + }, + { + "epoch": 0.0, + "learning_rate": 3.4786302471954576e-05, + "loss": 3.5822, + "step": 929280 + }, + { + "epoch": 0.0, + "learning_rate": 3.4777916524444056e-05, + "loss": 3.5863, + "step": 929792 + }, + { + "epoch": 0.0, + "learning_rate": 3.476954695573727e-05, + "loss": 3.5807, + "step": 930304 + }, + { + "epoch": 0.0, + "learning_rate": 3.4761161008226745e-05, + "loss": 3.5766, + "step": 930816 + }, + { + "epoch": 0.01, + "learning_rate": 3.4752775060716225e-05, + "loss": 3.5816, + "step": 931328 + }, + { + "epoch": 0.01, + "learning_rate": 3.4744389113205705e-05, + "loss": 3.5851, + "step": 931840 + }, + { + "epoch": 0.01, + "learning_rate": 3.4736019544498914e-05, + "loss": 3.5894, + "step": 932352 + }, + { + "epoch": 0.01, + "learning_rate": 3.4727633596988394e-05, + "loss": 3.5977, + "step": 932864 + }, + { + "epoch": 0.01, + "learning_rate": 3.4719247649477874e-05, + "loss": 3.583, + "step": 933376 + }, + { + "epoch": 0.01, + "learning_rate": 3.4710861701967354e-05, + "loss": 3.5858, + "step": 933888 + }, + { + "epoch": 0.01, + "learning_rate": 3.470249213326057e-05, + "loss": 3.5979, + "step": 934400 + }, + { + "epoch": 0.01, + "learning_rate": 3.469410618575005e-05, + "loss": 3.5775, + "step": 934912 + }, + { + "epoch": 0.01, + "learning_rate": 3.468572023823953e-05, + "loss": 3.5767, + "step": 935424 + }, + { + "epoch": 0.01, + "learning_rate": 3.467733429072901e-05, + "loss": 3.5794, + "step": 935936 + }, + { + "epoch": 0.01, + "learning_rate": 3.466896472202222e-05, + "loss": 3.5796, + "step": 936448 + }, + { + "epoch": 0.01, + "learning_rate": 3.46605787745117e-05, + "loss": 3.5788, + "step": 936960 + }, + { + "epoch": 0.01, + "learning_rate": 3.465219282700118e-05, + "loss": 3.5852, + "step": 937472 + }, + { + "epoch": 0.01, + "learning_rate": 3.464380687949066e-05, + "loss": 3.5856, + "step": 937984 + }, + { + "epoch": 0.01, + "learning_rate": 3.463543731078387e-05, + "loss": 3.5812, + "step": 938496 + }, + { + "epoch": 0.01, + "learning_rate": 3.462705136327335e-05, + "loss": 3.5881, + "step": 939008 + }, + { + "epoch": 0.01, + "learning_rate": 3.461866541576283e-05, + "loss": 3.5782, + "step": 939520 + }, + { + "epoch": 0.01, + "learning_rate": 3.461027946825231e-05, + "loss": 3.5784, + "step": 940032 + }, + { + "epoch": 0.01, + "learning_rate": 3.460190989954552e-05, + "loss": 3.5563, + "step": 940544 + }, + { + "epoch": 0.01, + "learning_rate": 3.4593523952035e-05, + "loss": 3.5943, + "step": 941056 + }, + { + "epoch": 0.01, + "learning_rate": 3.458513800452448e-05, + "loss": 3.5757, + "step": 941568 + }, + { + "epoch": 0.01, + "learning_rate": 3.457675205701396e-05, + "loss": 3.5838, + "step": 942080 + }, + { + "epoch": 0.01, + "learning_rate": 3.456838248830717e-05, + "loss": 3.5775, + "step": 942592 + }, + { + "epoch": 0.01, + "learning_rate": 3.455999654079665e-05, + "loss": 3.5757, + "step": 943104 + }, + { + "epoch": 0.01, + "learning_rate": 3.455161059328613e-05, + "loss": 3.5667, + "step": 943616 + }, + { + "epoch": 0.01, + "learning_rate": 3.454324102457934e-05, + "loss": 3.5747, + "step": 944128 + }, + { + "epoch": 0.01, + "learning_rate": 3.453485507706882e-05, + "loss": 3.5852, + "step": 944640 + }, + { + "epoch": 0.01, + "learning_rate": 3.45264691295583e-05, + "loss": 3.5691, + "step": 945152 + }, + { + "epoch": 0.01, + "learning_rate": 3.451808318204778e-05, + "loss": 3.5906, + "step": 945664 + }, + { + "epoch": 0.01, + "learning_rate": 3.4509713613341e-05, + "loss": 3.5787, + "step": 946176 + }, + { + "epoch": 0.01, + "learning_rate": 3.450132766583048e-05, + "loss": 3.5611, + "step": 946688 + }, + { + "epoch": 0.01, + "learning_rate": 3.449294171831996e-05, + "loss": 3.5875, + "step": 947200 + }, + { + "epoch": 0.01, + "learning_rate": 3.448455577080944e-05, + "loss": 3.5728, + "step": 947712 + }, + { + "epoch": 0.01, + "learning_rate": 3.4476186202102646e-05, + "loss": 3.5748, + "step": 948224 + }, + { + "epoch": 0.01, + "learning_rate": 3.4467800254592126e-05, + "loss": 3.5778, + "step": 948736 + }, + { + "epoch": 0.01, + "learning_rate": 3.4459414307081606e-05, + "loss": 3.58, + "step": 949248 + }, + { + "epoch": 0.01, + "learning_rate": 3.4451028359571086e-05, + "loss": 3.572, + "step": 949760 + }, + { + "epoch": 0.01, + "learning_rate": 3.4442658790864295e-05, + "loss": 3.5823, + "step": 950272 + }, + { + "epoch": 0.01, + "learning_rate": 3.4434272843353775e-05, + "loss": 3.565, + "step": 950784 + }, + { + "epoch": 0.01, + "learning_rate": 3.4425886895843255e-05, + "loss": 3.5688, + "step": 951296 + }, + { + "epoch": 0.01, + "learning_rate": 3.4417500948332735e-05, + "loss": 3.5818, + "step": 951808 + }, + { + "epoch": 0.01, + "learning_rate": 3.4409131379625944e-05, + "loss": 3.5797, + "step": 952320 + }, + { + "epoch": 0.01, + "learning_rate": 3.440074543211543e-05, + "loss": 3.5886, + "step": 952832 + }, + { + "epoch": 0.01, + "learning_rate": 3.439235948460491e-05, + "loss": 3.5764, + "step": 953344 + }, + { + "epoch": 0.01, + "learning_rate": 3.438397353709439e-05, + "loss": 3.5983, + "step": 953856 + }, + { + "epoch": 0.01, + "learning_rate": 3.43756039683876e-05, + "loss": 3.5732, + "step": 954368 + }, + { + "epoch": 0.01, + "learning_rate": 3.436721802087708e-05, + "loss": 3.5923, + "step": 954880 + }, + { + "epoch": 0.01, + "learning_rate": 3.435883207336656e-05, + "loss": 3.5737, + "step": 955392 + }, + { + "epoch": 0.01, + "learning_rate": 3.435044612585604e-05, + "loss": 3.5797, + "step": 955904 + }, + { + "epoch": 0.01, + "learning_rate": 3.434207655714925e-05, + "loss": 3.5718, + "step": 956416 + }, + { + "epoch": 0.01, + "learning_rate": 3.433369060963873e-05, + "loss": 3.5862, + "step": 956928 + }, + { + "epoch": 0.01, + "learning_rate": 3.432530466212821e-05, + "loss": 3.5826, + "step": 957440 + }, + { + "epoch": 0.01, + "learning_rate": 3.431691871461769e-05, + "loss": 3.5912, + "step": 957952 + }, + { + "epoch": 0.01, + "learning_rate": 3.430853276710717e-05, + "loss": 3.5704, + "step": 958464 + }, + { + "epoch": 0.01, + "learning_rate": 3.430014681959665e-05, + "loss": 3.5651, + "step": 958976 + }, + { + "epoch": 0.01, + "learning_rate": 3.429176087208613e-05, + "loss": 3.5754, + "step": 959488 + }, + { + "epoch": 0.01, + "learning_rate": 3.4283374924575615e-05, + "loss": 3.5867, + "step": 960000 + }, + { + "epoch": 0.01, + "learning_rate": 3.4275005355868824e-05, + "loss": 3.5751, + "step": 960512 + }, + { + "epoch": 0.01, + "learning_rate": 3.4266619408358304e-05, + "loss": 3.5827, + "step": 961024 + }, + { + "epoch": 0.01, + "learning_rate": 3.4258233460847784e-05, + "loss": 3.5742, + "step": 961536 + }, + { + "epoch": 0.02, + "learning_rate": 3.4249847513337264e-05, + "loss": 3.5698, + "step": 962048 + }, + { + "epoch": 0.02, + "learning_rate": 3.424147794463047e-05, + "loss": 3.5767, + "step": 962560 + }, + { + "epoch": 0.02, + "learning_rate": 3.423309199711995e-05, + "loss": 3.5682, + "step": 963072 + }, + { + "epoch": 0.02, + "learning_rate": 3.422470604960943e-05, + "loss": 3.5848, + "step": 963584 + }, + { + "epoch": 0.02, + "learning_rate": 3.421633648090264e-05, + "loss": 3.5927, + "step": 964096 + }, + { + "epoch": 0.02, + "learning_rate": 3.420795053339212e-05, + "loss": 3.5921, + "step": 964608 + }, + { + "epoch": 0.02, + "learning_rate": 3.41995645858816e-05, + "loss": 3.5689, + "step": 965120 + }, + { + "epoch": 0.02, + "learning_rate": 3.419117863837108e-05, + "loss": 3.5729, + "step": 965632 + }, + { + "epoch": 0.02, + "learning_rate": 3.418279269086057e-05, + "loss": 3.578, + "step": 966144 + }, + { + "epoch": 0.02, + "learning_rate": 3.417440674335005e-05, + "loss": 3.5806, + "step": 966656 + }, + { + "epoch": 0.02, + "learning_rate": 3.416602079583953e-05, + "loss": 3.5818, + "step": 967168 + }, + { + "epoch": 0.02, + "learning_rate": 3.4157634848329e-05, + "loss": 3.5828, + "step": 967680 + }, + { + "epoch": 0.02, + "learning_rate": 3.414926527962222e-05, + "loss": 3.5774, + "step": 968192 + }, + { + "epoch": 0.02, + "learning_rate": 3.41408793321117e-05, + "loss": 3.5725, + "step": 968704 + }, + { + "epoch": 0.02, + "learning_rate": 3.413249338460117e-05, + "loss": 3.5799, + "step": 969216 + }, + { + "epoch": 0.02, + "learning_rate": 3.412410743709065e-05, + "loss": 3.565, + "step": 969728 + }, + { + "epoch": 0.02, + "learning_rate": 3.411573786838387e-05, + "loss": 3.5714, + "step": 970240 + }, + { + "epoch": 0.02, + "learning_rate": 3.410735192087335e-05, + "loss": 3.5789, + "step": 970752 + }, + { + "epoch": 0.02, + "learning_rate": 3.409896597336282e-05, + "loss": 3.5801, + "step": 971264 + }, + { + "epoch": 0.02, + "learning_rate": 3.409058002585231e-05, + "loss": 3.5671, + "step": 971776 + }, + { + "epoch": 0.02, + "learning_rate": 3.408221045714552e-05, + "loss": 3.5774, + "step": 972288 + }, + { + "epoch": 0.02, + "learning_rate": 3.4073824509634996e-05, + "loss": 3.5566, + "step": 972800 + }, + { + "epoch": 0.02, + "learning_rate": 3.4065438562124476e-05, + "loss": 3.5808, + "step": 973312 + }, + { + "epoch": 0.02, + "learning_rate": 3.4057052614613956e-05, + "loss": 3.5794, + "step": 973824 + }, + { + "epoch": 0.02, + "learning_rate": 3.404868304590717e-05, + "loss": 3.5799, + "step": 974336 + }, + { + "epoch": 0.02, + "learning_rate": 3.4040297098396645e-05, + "loss": 3.586, + "step": 974848 + }, + { + "epoch": 0.02, + "learning_rate": 3.4031911150886125e-05, + "loss": 3.5901, + "step": 975360 + }, + { + "epoch": 0.02, + "learning_rate": 3.4023525203375605e-05, + "loss": 3.573, + "step": 975872 + }, + { + "epoch": 0.02, + "learning_rate": 3.401515563466882e-05, + "loss": 3.5732, + "step": 976384 + }, + { + "epoch": 0.02, + "learning_rate": 3.4006769687158294e-05, + "loss": 3.5799, + "step": 976896 + }, + { + "epoch": 0.02, + "learning_rate": 3.3998383739647774e-05, + "loss": 3.5783, + "step": 977408 + }, + { + "epoch": 0.02, + "learning_rate": 3.398999779213726e-05, + "loss": 3.5709, + "step": 977920 + }, + { + "epoch": 0.02, + "learning_rate": 3.398162822343047e-05, + "loss": 3.5701, + "step": 978432 + }, + { + "epoch": 0.02, + "learning_rate": 3.397324227591995e-05, + "loss": 3.574, + "step": 978944 + }, + { + "epoch": 0.02, + "learning_rate": 3.396485632840943e-05, + "loss": 3.5738, + "step": 979456 + }, + { + "epoch": 0.02, + "learning_rate": 3.3956486759702645e-05, + "loss": 3.5691, + "step": 979968 + }, + { + "epoch": 0.02, + "learning_rate": 3.394810081219212e-05, + "loss": 3.5722, + "step": 980480 + }, + { + "epoch": 0.02, + "learning_rate": 3.39397148646816e-05, + "loss": 3.5742, + "step": 980992 + }, + { + "epoch": 0.02, + "learning_rate": 3.393132891717108e-05, + "loss": 3.5635, + "step": 981504 + }, + { + "epoch": 0.02, + "learning_rate": 3.3922959348464294e-05, + "loss": 3.5834, + "step": 982016 + }, + { + "epoch": 0.02, + "learning_rate": 3.391457340095377e-05, + "loss": 3.5765, + "step": 982528 + }, + { + "epoch": 0.02, + "learning_rate": 3.390618745344325e-05, + "loss": 3.5928, + "step": 983040 + }, + { + "epoch": 0.02, + "learning_rate": 3.389780150593273e-05, + "loss": 3.5607, + "step": 983552 + }, + { + "epoch": 0.02, + "learning_rate": 3.388943193722594e-05, + "loss": 3.5833, + "step": 984064 + }, + { + "epoch": 0.02, + "learning_rate": 3.388104598971542e-05, + "loss": 3.5802, + "step": 984576 + }, + { + "epoch": 0.02, + "learning_rate": 3.38726600422049e-05, + "loss": 3.5733, + "step": 985088 + }, + { + "epoch": 0.02, + "learning_rate": 3.386427409469438e-05, + "loss": 3.5789, + "step": 985600 + }, + { + "epoch": 0.02, + "learning_rate": 3.385590452598759e-05, + "loss": 3.5732, + "step": 986112 + }, + { + "epoch": 0.02, + "learning_rate": 3.384751857847707e-05, + "loss": 3.5818, + "step": 986624 + }, + { + "epoch": 0.02, + "learning_rate": 3.383913263096655e-05, + "loss": 3.5854, + "step": 987136 + }, + { + "epoch": 0.02, + "learning_rate": 3.383074668345603e-05, + "loss": 3.5712, + "step": 987648 + }, + { + "epoch": 0.02, + "learning_rate": 3.382237711474924e-05, + "loss": 3.5769, + "step": 988160 + }, + { + "epoch": 0.02, + "learning_rate": 3.381399116723872e-05, + "loss": 3.576, + "step": 988672 + }, + { + "epoch": 0.02, + "learning_rate": 3.38056052197282e-05, + "loss": 3.5732, + "step": 989184 + }, + { + "epoch": 0.02, + "learning_rate": 3.379721927221768e-05, + "loss": 3.5715, + "step": 989696 + }, + { + "epoch": 0.02, + "learning_rate": 3.37888497035109e-05, + "loss": 3.58, + "step": 990208 + }, + { + "epoch": 0.02, + "learning_rate": 3.378046375600038e-05, + "loss": 3.5724, + "step": 990720 + }, + { + "epoch": 0.02, + "learning_rate": 3.377207780848986e-05, + "loss": 3.5781, + "step": 991232 + }, + { + "epoch": 0.02, + "learning_rate": 3.376369186097934e-05, + "loss": 3.5679, + "step": 991744 + }, + { + "epoch": 0.03, + "eval_loss": 3.84108567237854, + "eval_runtime": 308.6212, + "eval_samples_per_second": 1236.438, + "eval_steps_per_second": 38.64, + "step": 992160 + }, + { + "epoch": 1.0, + "learning_rate": 3.3755322292272546e-05, + "loss": 3.5769, + "step": 992256 + }, + { + "epoch": 1.0, + "learning_rate": 3.3746936344762026e-05, + "loss": 3.5592, + "step": 992768 + }, + { + "epoch": 1.0, + "learning_rate": 3.3738550397251506e-05, + "loss": 3.5688, + "step": 993280 + }, + { + "epoch": 1.0, + "learning_rate": 3.3730164449740986e-05, + "loss": 3.5843, + "step": 993792 + }, + { + "epoch": 1.0, + "learning_rate": 3.3721794881034195e-05, + "loss": 3.5783, + "step": 994304 + }, + { + "epoch": 1.0, + "learning_rate": 3.3713408933523675e-05, + "loss": 3.5756, + "step": 994816 + }, + { + "epoch": 1.0, + "learning_rate": 3.3705022986013155e-05, + "loss": 3.5733, + "step": 995328 + }, + { + "epoch": 1.0, + "learning_rate": 3.3696637038502635e-05, + "loss": 3.5704, + "step": 995840 + }, + { + "epoch": 1.0, + "learning_rate": 3.368826746979585e-05, + "loss": 3.5599, + "step": 996352 + }, + { + "epoch": 1.0, + "learning_rate": 3.367988152228533e-05, + "loss": 3.5756, + "step": 996864 + }, + { + "epoch": 1.0, + "learning_rate": 3.367149557477481e-05, + "loss": 3.5722, + "step": 997376 + }, + { + "epoch": 1.0, + "learning_rate": 3.366310962726429e-05, + "loss": 3.5743, + "step": 997888 + }, + { + "epoch": 1.0, + "learning_rate": 3.36547400585575e-05, + "loss": 3.5793, + "step": 998400 + }, + { + "epoch": 1.0, + "learning_rate": 3.364635411104698e-05, + "loss": 3.5615, + "step": 998912 + }, + { + "epoch": 1.0, + "learning_rate": 3.363796816353646e-05, + "loss": 3.5623, + "step": 999424 + }, + { + "epoch": 1.0, + "learning_rate": 3.362958221602594e-05, + "loss": 3.5608, + "step": 999936 + }, + { + "epoch": 1.0, + "learning_rate": 3.362121264731915e-05, + "loss": 3.571, + "step": 1000448 + }, + { + "epoch": 1.0, + "learning_rate": 3.361282669980863e-05, + "loss": 3.5677, + "step": 1000960 + }, + { + "epoch": 1.0, + "learning_rate": 3.360444075229811e-05, + "loss": 3.5637, + "step": 1001472 + }, + { + "epoch": 1.0, + "learning_rate": 3.359605480478759e-05, + "loss": 3.5685, + "step": 1001984 + }, + { + "epoch": 1.0, + "learning_rate": 3.3587685236080804e-05, + "loss": 3.58, + "step": 1002496 + }, + { + "epoch": 1.0, + "learning_rate": 3.3579299288570284e-05, + "loss": 3.5745, + "step": 1003008 + }, + { + "epoch": 1.0, + "learning_rate": 3.3570913341059764e-05, + "loss": 3.5706, + "step": 1003520 + }, + { + "epoch": 1.0, + "learning_rate": 3.3562527393549244e-05, + "loss": 3.5677, + "step": 1004032 + }, + { + "epoch": 1.0, + "learning_rate": 3.355415782484245e-05, + "loss": 3.5719, + "step": 1004544 + }, + { + "epoch": 1.0, + "learning_rate": 3.354577187733193e-05, + "loss": 3.5714, + "step": 1005056 + }, + { + "epoch": 1.0, + "learning_rate": 3.353738592982141e-05, + "loss": 3.5658, + "step": 1005568 + }, + { + "epoch": 1.0, + "learning_rate": 3.352899998231089e-05, + "loss": 3.5702, + "step": 1006080 + }, + { + "epoch": 1.0, + "learning_rate": 3.35206304136041e-05, + "loss": 3.5594, + "step": 1006592 + }, + { + "epoch": 1.0, + "learning_rate": 3.351224446609358e-05, + "loss": 3.5584, + "step": 1007104 + }, + { + "epoch": 1.01, + "learning_rate": 3.350385851858306e-05, + "loss": 3.5634, + "step": 1007616 + }, + { + "epoch": 1.01, + "learning_rate": 3.349547257107254e-05, + "loss": 3.5661, + "step": 1008128 + }, + { + "epoch": 1.01, + "learning_rate": 3.348710300236576e-05, + "loss": 3.5761, + "step": 1008640 + }, + { + "epoch": 1.01, + "learning_rate": 3.347871705485524e-05, + "loss": 3.5757, + "step": 1009152 + }, + { + "epoch": 1.01, + "learning_rate": 3.347033110734472e-05, + "loss": 3.5662, + "step": 1009664 + }, + { + "epoch": 1.01, + "learning_rate": 3.34619451598342e-05, + "loss": 3.571, + "step": 1010176 + }, + { + "epoch": 1.01, + "learning_rate": 3.345357559112741e-05, + "loss": 3.5805, + "step": 1010688 + }, + { + "epoch": 1.01, + "learning_rate": 3.344518964361689e-05, + "loss": 3.5538, + "step": 1011200 + }, + { + "epoch": 1.01, + "learning_rate": 3.343680369610637e-05, + "loss": 3.5639, + "step": 1011712 + }, + { + "epoch": 1.01, + "learning_rate": 3.3428417748595847e-05, + "loss": 3.5632, + "step": 1012224 + }, + { + "epoch": 1.01, + "learning_rate": 3.3420048179889056e-05, + "loss": 3.562, + "step": 1012736 + }, + { + "epoch": 1.01, + "learning_rate": 3.3411662232378536e-05, + "loss": 3.5625, + "step": 1013248 + }, + { + "epoch": 1.01, + "learning_rate": 3.3403276284868016e-05, + "loss": 3.568, + "step": 1013760 + }, + { + "epoch": 1.01, + "learning_rate": 3.3394890337357496e-05, + "loss": 3.5718, + "step": 1014272 + }, + { + "epoch": 1.01, + "learning_rate": 3.338652076865071e-05, + "loss": 3.5625, + "step": 1014784 + }, + { + "epoch": 1.01, + "learning_rate": 3.337813482114019e-05, + "loss": 3.5687, + "step": 1015296 + }, + { + "epoch": 1.01, + "learning_rate": 3.336974887362967e-05, + "loss": 3.5609, + "step": 1015808 + }, + { + "epoch": 1.01, + "learning_rate": 3.336136292611915e-05, + "loss": 3.5579, + "step": 1016320 + }, + { + "epoch": 1.01, + "learning_rate": 3.335299335741236e-05, + "loss": 3.5435, + "step": 1016832 + }, + { + "epoch": 1.01, + "learning_rate": 3.334460740990184e-05, + "loss": 3.5747, + "step": 1017344 + }, + { + "epoch": 1.01, + "learning_rate": 3.333622146239132e-05, + "loss": 3.5604, + "step": 1017856 + }, + { + "epoch": 1.01, + "learning_rate": 3.33278355148808e-05, + "loss": 3.5676, + "step": 1018368 + }, + { + "epoch": 1.01, + "learning_rate": 3.331946594617401e-05, + "loss": 3.5612, + "step": 1018880 + }, + { + "epoch": 1.01, + "learning_rate": 3.331107999866349e-05, + "loss": 3.5548, + "step": 1019392 + }, + { + "epoch": 1.01, + "learning_rate": 3.330269405115297e-05, + "loss": 3.5512, + "step": 1019904 + }, + { + "epoch": 1.01, + "learning_rate": 3.329430810364245e-05, + "loss": 3.5582, + "step": 1020416 + }, + { + "epoch": 1.01, + "learning_rate": 3.3285938534935665e-05, + "loss": 3.5677, + "step": 1020928 + }, + { + "epoch": 1.01, + "learning_rate": 3.3277552587425145e-05, + "loss": 3.5491, + "step": 1021440 + }, + { + "epoch": 1.01, + "learning_rate": 3.3269166639914625e-05, + "loss": 3.5776, + "step": 1021952 + }, + { + "epoch": 1.01, + "learning_rate": 3.3260797071207834e-05, + "loss": 3.5628, + "step": 1022464 + }, + { + "epoch": 1.01, + "learning_rate": 3.3252411123697314e-05, + "loss": 3.5447, + "step": 1022976 + }, + { + "epoch": 1.01, + "learning_rate": 3.3244025176186794e-05, + "loss": 3.5686, + "step": 1023488 + }, + { + "epoch": 1.01, + "learning_rate": 3.3235639228676274e-05, + "loss": 3.5554, + "step": 1024000 + }, + { + "epoch": 1.01, + "learning_rate": 3.322726965996948e-05, + "loss": 3.5605, + "step": 1024512 + }, + { + "epoch": 1.01, + "learning_rate": 3.321888371245896e-05, + "loss": 3.554, + "step": 1025024 + }, + { + "epoch": 1.01, + "learning_rate": 3.321049776494844e-05, + "loss": 3.5683, + "step": 1025536 + }, + { + "epoch": 1.01, + "learning_rate": 3.320211181743792e-05, + "loss": 3.5513, + "step": 1026048 + }, + { + "epoch": 1.01, + "learning_rate": 3.319374224873114e-05, + "loss": 3.5662, + "step": 1026560 + }, + { + "epoch": 1.01, + "learning_rate": 3.318535630122062e-05, + "loss": 3.5464, + "step": 1027072 + }, + { + "epoch": 1.01, + "learning_rate": 3.31769703537101e-05, + "loss": 3.5552, + "step": 1027584 + }, + { + "epoch": 1.01, + "learning_rate": 3.316858440619958e-05, + "loss": 3.5626, + "step": 1028096 + }, + { + "epoch": 1.01, + "learning_rate": 3.316021483749279e-05, + "loss": 3.569, + "step": 1028608 + }, + { + "epoch": 1.01, + "learning_rate": 3.315182888998227e-05, + "loss": 3.5653, + "step": 1029120 + }, + { + "epoch": 1.01, + "learning_rate": 3.314344294247175e-05, + "loss": 3.5607, + "step": 1029632 + }, + { + "epoch": 1.01, + "learning_rate": 3.313505699496123e-05, + "loss": 3.5816, + "step": 1030144 + }, + { + "epoch": 1.01, + "learning_rate": 3.312668742625444e-05, + "loss": 3.5576, + "step": 1030656 + }, + { + "epoch": 1.01, + "learning_rate": 3.311830147874392e-05, + "loss": 3.5707, + "step": 1031168 + }, + { + "epoch": 1.01, + "learning_rate": 3.31099155312334e-05, + "loss": 3.5604, + "step": 1031680 + }, + { + "epoch": 1.01, + "learning_rate": 3.3101529583722877e-05, + "loss": 3.5624, + "step": 1032192 + }, + { + "epoch": 1.01, + "learning_rate": 3.309316001501609e-05, + "loss": 3.5592, + "step": 1032704 + }, + { + "epoch": 1.01, + "learning_rate": 3.308477406750557e-05, + "loss": 3.5642, + "step": 1033216 + }, + { + "epoch": 1.01, + "learning_rate": 3.307638811999505e-05, + "loss": 3.5674, + "step": 1033728 + }, + { + "epoch": 1.01, + "learning_rate": 3.306800217248453e-05, + "loss": 3.5716, + "step": 1034240 + }, + { + "epoch": 1.01, + "learning_rate": 3.305961622497401e-05, + "loss": 3.5582, + "step": 1034752 + }, + { + "epoch": 1.01, + "learning_rate": 3.305123027746349e-05, + "loss": 3.5458, + "step": 1035264 + }, + { + "epoch": 1.01, + "learning_rate": 3.3042844329952965e-05, + "loss": 3.5568, + "step": 1035776 + }, + { + "epoch": 1.01, + "learning_rate": 3.3034458382442445e-05, + "loss": 3.5676, + "step": 1036288 + }, + { + "epoch": 1.01, + "learning_rate": 3.302608881373566e-05, + "loss": 3.5588, + "step": 1036800 + }, + { + "epoch": 1.01, + "learning_rate": 3.301770286622514e-05, + "loss": 3.5644, + "step": 1037312 + }, + { + "epoch": 1.01, + "learning_rate": 3.3009316918714614e-05, + "loss": 3.5573, + "step": 1037824 + }, + { + "epoch": 1.02, + "learning_rate": 3.3000930971204094e-05, + "loss": 3.5523, + "step": 1038336 + }, + { + "epoch": 1.02, + "learning_rate": 3.299256140249731e-05, + "loss": 3.5604, + "step": 1038848 + }, + { + "epoch": 1.02, + "learning_rate": 3.298417545498679e-05, + "loss": 3.5507, + "step": 1039360 + }, + { + "epoch": 1.02, + "learning_rate": 3.297578950747627e-05, + "loss": 3.571, + "step": 1039872 + }, + { + "epoch": 1.02, + "learning_rate": 3.296740355996575e-05, + "loss": 3.57, + "step": 1040384 + }, + { + "epoch": 1.02, + "learning_rate": 3.2959033991258966e-05, + "loss": 3.5741, + "step": 1040896 + }, + { + "epoch": 1.02, + "learning_rate": 3.295064804374844e-05, + "loss": 3.5511, + "step": 1041408 + }, + { + "epoch": 1.02, + "learning_rate": 3.294226209623792e-05, + "loss": 3.5601, + "step": 1041920 + }, + { + "epoch": 1.02, + "learning_rate": 3.29338761487274e-05, + "loss": 3.5607, + "step": 1042432 + }, + { + "epoch": 1.02, + "learning_rate": 3.2925506580020615e-05, + "loss": 3.5619, + "step": 1042944 + }, + { + "epoch": 1.02, + "learning_rate": 3.291712063251009e-05, + "loss": 3.5685, + "step": 1043456 + }, + { + "epoch": 1.02, + "learning_rate": 3.290873468499957e-05, + "loss": 3.5632, + "step": 1043968 + }, + { + "epoch": 1.02, + "learning_rate": 3.290034873748905e-05, + "loss": 3.5601, + "step": 1044480 + }, + { + "epoch": 1.02, + "learning_rate": 3.2891979168782264e-05, + "loss": 3.555, + "step": 1044992 + }, + { + "epoch": 1.02, + "learning_rate": 3.2883593221271744e-05, + "loss": 3.5678, + "step": 1045504 + }, + { + "epoch": 1.02, + "learning_rate": 3.2875207273761224e-05, + "loss": 3.5456, + "step": 1046016 + }, + { + "epoch": 1.02, + "learning_rate": 3.2866821326250704e-05, + "loss": 3.5528, + "step": 1046528 + }, + { + "epoch": 1.02, + "learning_rate": 3.285845175754391e-05, + "loss": 3.5635, + "step": 1047040 + }, + { + "epoch": 1.02, + "learning_rate": 3.285006581003339e-05, + "loss": 3.5626, + "step": 1047552 + }, + { + "epoch": 1.02, + "learning_rate": 3.284167986252287e-05, + "loss": 3.5507, + "step": 1048064 + }, + { + "epoch": 1.02, + "learning_rate": 3.283329391501235e-05, + "loss": 3.5622, + "step": 1048576 + }, + { + "epoch": 1.02, + "learning_rate": 3.282492434630556e-05, + "loss": 3.541, + "step": 1049088 + }, + { + "epoch": 1.02, + "learning_rate": 3.281653839879504e-05, + "loss": 3.5666, + "step": 1049600 + }, + { + "epoch": 1.02, + "learning_rate": 3.280815245128452e-05, + "loss": 3.5576, + "step": 1050112 + }, + { + "epoch": 1.02, + "learning_rate": 3.2799766503774e-05, + "loss": 3.5641, + "step": 1050624 + }, + { + "epoch": 1.02, + "learning_rate": 3.279139693506722e-05, + "loss": 3.5696, + "step": 1051136 + }, + { + "epoch": 1.02, + "learning_rate": 3.27830109875567e-05, + "loss": 3.5719, + "step": 1051648 + }, + { + "epoch": 1.02, + "learning_rate": 3.277462504004618e-05, + "loss": 3.5557, + "step": 1052160 + }, + { + "epoch": 1.02, + "learning_rate": 3.2766255471339387e-05, + "loss": 3.5586, + "step": 1052672 + }, + { + "epoch": 1.02, + "learning_rate": 3.2757869523828867e-05, + "loss": 3.5634, + "step": 1053184 + }, + { + "epoch": 1.02, + "learning_rate": 3.2749483576318346e-05, + "loss": 3.5563, + "step": 1053696 + }, + { + "epoch": 1.02, + "learning_rate": 3.2741097628807826e-05, + "loss": 3.559, + "step": 1054208 + }, + { + "epoch": 1.02, + "learning_rate": 3.2732728060101036e-05, + "loss": 3.551, + "step": 1054720 + }, + { + "epoch": 1.02, + "learning_rate": 3.2724342112590515e-05, + "loss": 3.5594, + "step": 1055232 + }, + { + "epoch": 1.02, + "learning_rate": 3.2715956165079995e-05, + "loss": 3.5522, + "step": 1055744 + }, + { + "epoch": 1.02, + "learning_rate": 3.2707570217569475e-05, + "loss": 3.5518, + "step": 1056256 + }, + { + "epoch": 1.02, + "learning_rate": 3.2699200648862684e-05, + "loss": 3.5589, + "step": 1056768 + }, + { + "epoch": 1.02, + "learning_rate": 3.269081470135217e-05, + "loss": 3.5553, + "step": 1057280 + }, + { + "epoch": 1.02, + "learning_rate": 3.268242875384165e-05, + "loss": 3.5498, + "step": 1057792 + }, + { + "epoch": 1.02, + "learning_rate": 3.267404280633113e-05, + "loss": 3.5661, + "step": 1058304 + }, + { + "epoch": 1.02, + "learning_rate": 3.266567323762434e-05, + "loss": 3.5593, + "step": 1058816 + }, + { + "epoch": 1.02, + "learning_rate": 3.265728729011382e-05, + "loss": 3.5741, + "step": 1059328 + }, + { + "epoch": 1.02, + "learning_rate": 3.26489013426033e-05, + "loss": 3.5507, + "step": 1059840 + }, + { + "epoch": 1.02, + "learning_rate": 3.264051539509278e-05, + "loss": 3.562, + "step": 1060352 + }, + { + "epoch": 1.02, + "learning_rate": 3.263214582638599e-05, + "loss": 3.5625, + "step": 1060864 + }, + { + "epoch": 1.02, + "learning_rate": 3.262375987887547e-05, + "loss": 3.5598, + "step": 1061376 + }, + { + "epoch": 1.02, + "learning_rate": 3.261537393136495e-05, + "loss": 3.5579, + "step": 1061888 + }, + { + "epoch": 1.02, + "learning_rate": 3.260698798385443e-05, + "loss": 3.5554, + "step": 1062400 + }, + { + "epoch": 1.02, + "learning_rate": 3.259861841514764e-05, + "loss": 3.5647, + "step": 1062912 + }, + { + "epoch": 1.02, + "learning_rate": 3.2590232467637125e-05, + "loss": 3.5677, + "step": 1063424 + }, + { + "epoch": 1.02, + "learning_rate": 3.2581846520126605e-05, + "loss": 3.5567, + "step": 1063936 + }, + { + "epoch": 1.02, + "learning_rate": 3.2573460572616085e-05, + "loss": 3.5555, + "step": 1064448 + }, + { + "epoch": 1.02, + "learning_rate": 3.256510738271303e-05, + "loss": 3.5607, + "step": 1064960 + }, + { + "epoch": 1.02, + "learning_rate": 3.255672143520251e-05, + "loss": 3.5574, + "step": 1065472 + }, + { + "epoch": 1.02, + "learning_rate": 3.254833548769198e-05, + "loss": 3.5514, + "step": 1065984 + }, + { + "epoch": 1.02, + "learning_rate": 3.253994954018146e-05, + "loss": 3.5653, + "step": 1066496 + }, + { + "epoch": 1.02, + "learning_rate": 3.253156359267094e-05, + "loss": 3.5553, + "step": 1067008 + }, + { + "epoch": 1.02, + "learning_rate": 3.252317764516042e-05, + "loss": 3.5646, + "step": 1067520 + }, + { + "epoch": 1.02, + "learning_rate": 3.25147916976499e-05, + "loss": 3.5481, + "step": 1068032 + }, + { + "epoch": 1.03, + "eval_loss": 3.8400161266326904, + "eval_runtime": 309.2364, + "eval_samples_per_second": 1233.978, + "eval_steps_per_second": 38.563, + "step": 1068480 + }, + { + "epoch": 0.0, + "learning_rate": 3.250640575013938e-05, + "loss": 3.5714, + "step": 1068544 + }, + { + "epoch": 0.0, + "learning_rate": 3.249801980262886e-05, + "loss": 3.5455, + "step": 1069056 + }, + { + "epoch": 0.0, + "learning_rate": 3.248963385511834e-05, + "loss": 3.5509, + "step": 1069568 + }, + { + "epoch": 0.0, + "learning_rate": 3.248124790760782e-05, + "loss": 3.5657, + "step": 1070080 + }, + { + "epoch": 0.0, + "learning_rate": 3.247287833890104e-05, + "loss": 3.564, + "step": 1070592 + }, + { + "epoch": 0.0, + "learning_rate": 3.246449239139052e-05, + "loss": 3.5601, + "step": 1071104 + }, + { + "epoch": 0.0, + "learning_rate": 3.245610644388e-05, + "loss": 3.5526, + "step": 1071616 + }, + { + "epoch": 0.0, + "learning_rate": 3.244772049636948e-05, + "loss": 3.5527, + "step": 1072128 + }, + { + "epoch": 0.0, + "learning_rate": 3.243935092766269e-05, + "loss": 3.5444, + "step": 1072640 + }, + { + "epoch": 0.0, + "learning_rate": 3.243096498015217e-05, + "loss": 3.5614, + "step": 1073152 + }, + { + "epoch": 0.0, + "learning_rate": 3.242257903264165e-05, + "loss": 3.5544, + "step": 1073664 + }, + { + "epoch": 0.0, + "learning_rate": 3.241419308513113e-05, + "loss": 3.5621, + "step": 1074176 + }, + { + "epoch": 0.0, + "learning_rate": 3.2405823516424336e-05, + "loss": 3.5569, + "step": 1074688 + }, + { + "epoch": 0.0, + "learning_rate": 3.2397437568913816e-05, + "loss": 3.5456, + "step": 1075200 + }, + { + "epoch": 0.0, + "learning_rate": 3.2389051621403296e-05, + "loss": 3.5485, + "step": 1075712 + }, + { + "epoch": 0.0, + "learning_rate": 3.2380665673892776e-05, + "loss": 3.5434, + "step": 1076224 + }, + { + "epoch": 0.0, + "learning_rate": 3.237229610518599e-05, + "loss": 3.5562, + "step": 1076736 + }, + { + "epoch": 0.0, + "learning_rate": 3.236391015767547e-05, + "loss": 3.5451, + "step": 1077248 + }, + { + "epoch": 0.0, + "learning_rate": 3.235552421016495e-05, + "loss": 3.5504, + "step": 1077760 + }, + { + "epoch": 0.0, + "learning_rate": 3.234713826265443e-05, + "loss": 3.5529, + "step": 1078272 + }, + { + "epoch": 0.0, + "learning_rate": 3.233876869394764e-05, + "loss": 3.5602, + "step": 1078784 + }, + { + "epoch": 0.0, + "learning_rate": 3.233038274643712e-05, + "loss": 3.5597, + "step": 1079296 + }, + { + "epoch": 0.0, + "learning_rate": 3.23219967989266e-05, + "loss": 3.5543, + "step": 1079808 + }, + { + "epoch": 0.0, + "learning_rate": 3.231361085141608e-05, + "loss": 3.5499, + "step": 1080320 + }, + { + "epoch": 0.0, + "learning_rate": 3.230524128270929e-05, + "loss": 3.5614, + "step": 1080832 + }, + { + "epoch": 0.0, + "learning_rate": 3.229685533519877e-05, + "loss": 3.5498, + "step": 1081344 + }, + { + "epoch": 0.0, + "learning_rate": 3.228846938768825e-05, + "loss": 3.546, + "step": 1081856 + }, + { + "epoch": 0.0, + "learning_rate": 3.228008344017773e-05, + "loss": 3.5572, + "step": 1082368 + }, + { + "epoch": 0.0, + "learning_rate": 3.2271730250274675e-05, + "loss": 3.5408, + "step": 1082880 + }, + { + "epoch": 0.0, + "learning_rate": 3.2263344302764155e-05, + "loss": 3.5403, + "step": 1083392 + }, + { + "epoch": 0.01, + "learning_rate": 3.2254958355253635e-05, + "loss": 3.5473, + "step": 1083904 + }, + { + "epoch": 0.01, + "learning_rate": 3.2246572407743115e-05, + "loss": 3.5475, + "step": 1084416 + }, + { + "epoch": 0.01, + "learning_rate": 3.2238186460232595e-05, + "loss": 3.5625, + "step": 1084928 + }, + { + "epoch": 0.01, + "learning_rate": 3.2229800512722075e-05, + "loss": 3.5616, + "step": 1085440 + }, + { + "epoch": 0.01, + "learning_rate": 3.2221414565211555e-05, + "loss": 3.5455, + "step": 1085952 + }, + { + "epoch": 0.01, + "learning_rate": 3.2213028617701035e-05, + "loss": 3.5574, + "step": 1086464 + }, + { + "epoch": 0.01, + "learning_rate": 3.2204659048994244e-05, + "loss": 3.5628, + "step": 1086976 + }, + { + "epoch": 0.01, + "learning_rate": 3.2196273101483724e-05, + "loss": 3.5421, + "step": 1087488 + }, + { + "epoch": 0.01, + "learning_rate": 3.2187887153973204e-05, + "loss": 3.5473, + "step": 1088000 + }, + { + "epoch": 0.01, + "learning_rate": 3.2179501206462684e-05, + "loss": 3.545, + "step": 1088512 + }, + { + "epoch": 0.01, + "learning_rate": 3.21711316377559e-05, + "loss": 3.5445, + "step": 1089024 + }, + { + "epoch": 0.01, + "learning_rate": 3.216274569024538e-05, + "loss": 3.5499, + "step": 1089536 + }, + { + "epoch": 0.01, + "learning_rate": 3.215435974273486e-05, + "loss": 3.5563, + "step": 1090048 + }, + { + "epoch": 0.01, + "learning_rate": 3.214597379522434e-05, + "loss": 3.5482, + "step": 1090560 + }, + { + "epoch": 0.01, + "learning_rate": 3.213760422651755e-05, + "loss": 3.5478, + "step": 1091072 + }, + { + "epoch": 0.01, + "learning_rate": 3.212921827900703e-05, + "loss": 3.5531, + "step": 1091584 + }, + { + "epoch": 0.01, + "learning_rate": 3.212083233149651e-05, + "loss": 3.5447, + "step": 1092096 + }, + { + "epoch": 0.01, + "learning_rate": 3.211244638398599e-05, + "loss": 3.5425, + "step": 1092608 + }, + { + "epoch": 0.01, + "learning_rate": 3.21040768152792e-05, + "loss": 3.5258, + "step": 1093120 + }, + { + "epoch": 0.01, + "learning_rate": 3.209569086776868e-05, + "loss": 3.5545, + "step": 1093632 + }, + { + "epoch": 0.01, + "learning_rate": 3.208730492025816e-05, + "loss": 3.5475, + "step": 1094144 + }, + { + "epoch": 0.01, + "learning_rate": 3.207891897274764e-05, + "loss": 3.5531, + "step": 1094656 + }, + { + "epoch": 0.01, + "learning_rate": 3.207054940404085e-05, + "loss": 3.5438, + "step": 1095168 + }, + { + "epoch": 0.01, + "learning_rate": 3.206216345653033e-05, + "loss": 3.5379, + "step": 1095680 + }, + { + "epoch": 0.01, + "learning_rate": 3.205377750901981e-05, + "loss": 3.5364, + "step": 1096192 + }, + { + "epoch": 0.01, + "learning_rate": 3.2045391561509286e-05, + "loss": 3.5416, + "step": 1096704 + }, + { + "epoch": 0.01, + "learning_rate": 3.20370219928025e-05, + "loss": 3.5493, + "step": 1097216 + }, + { + "epoch": 0.01, + "learning_rate": 3.202863604529198e-05, + "loss": 3.5305, + "step": 1097728 + }, + { + "epoch": 0.01, + "learning_rate": 3.202025009778146e-05, + "loss": 3.5595, + "step": 1098240 + }, + { + "epoch": 0.01, + "learning_rate": 3.2011864150270935e-05, + "loss": 3.5459, + "step": 1098752 + }, + { + "epoch": 0.01, + "learning_rate": 3.200349458156415e-05, + "loss": 3.5326, + "step": 1099264 + }, + { + "epoch": 0.01, + "learning_rate": 3.199510863405363e-05, + "loss": 3.5508, + "step": 1099776 + }, + { + "epoch": 0.01, + "learning_rate": 3.198672268654311e-05, + "loss": 3.5402, + "step": 1100288 + }, + { + "epoch": 0.01, + "learning_rate": 3.197835311783633e-05, + "loss": 3.5432, + "step": 1100800 + }, + { + "epoch": 0.01, + "learning_rate": 3.196996717032581e-05, + "loss": 3.5366, + "step": 1101312 + }, + { + "epoch": 0.01, + "learning_rate": 3.196158122281529e-05, + "loss": 3.5525, + "step": 1101824 + }, + { + "epoch": 0.01, + "learning_rate": 3.195319527530476e-05, + "loss": 3.5395, + "step": 1102336 + }, + { + "epoch": 0.01, + "learning_rate": 3.1944825706597976e-05, + "loss": 3.5425, + "step": 1102848 + }, + { + "epoch": 0.01, + "learning_rate": 3.1936439759087456e-05, + "loss": 3.5378, + "step": 1103360 + }, + { + "epoch": 0.01, + "learning_rate": 3.1928053811576936e-05, + "loss": 3.537, + "step": 1103872 + }, + { + "epoch": 0.01, + "learning_rate": 3.191966786406641e-05, + "loss": 3.5429, + "step": 1104384 + }, + { + "epoch": 0.01, + "learning_rate": 3.1911298295359625e-05, + "loss": 3.5575, + "step": 1104896 + }, + { + "epoch": 0.01, + "learning_rate": 3.1902912347849105e-05, + "loss": 3.5484, + "step": 1105408 + }, + { + "epoch": 0.01, + "learning_rate": 3.1894526400338585e-05, + "loss": 3.5455, + "step": 1105920 + }, + { + "epoch": 0.01, + "learning_rate": 3.1886140452828065e-05, + "loss": 3.5613, + "step": 1106432 + }, + { + "epoch": 0.01, + "learning_rate": 3.187777088412128e-05, + "loss": 3.5426, + "step": 1106944 + }, + { + "epoch": 0.01, + "learning_rate": 3.186938493661076e-05, + "loss": 3.5525, + "step": 1107456 + }, + { + "epoch": 0.01, + "learning_rate": 3.1860998989100234e-05, + "loss": 3.546, + "step": 1107968 + }, + { + "epoch": 0.01, + "learning_rate": 3.1852613041589714e-05, + "loss": 3.5494, + "step": 1108480 + }, + { + "epoch": 0.01, + "learning_rate": 3.184424347288293e-05, + "loss": 3.5425, + "step": 1108992 + }, + { + "epoch": 0.01, + "learning_rate": 3.183585752537241e-05, + "loss": 3.5462, + "step": 1109504 + }, + { + "epoch": 0.01, + "learning_rate": 3.182747157786188e-05, + "loss": 3.5512, + "step": 1110016 + }, + { + "epoch": 0.01, + "learning_rate": 3.181908563035136e-05, + "loss": 3.5567, + "step": 1110528 + }, + { + "epoch": 0.01, + "learning_rate": 3.181069968284084e-05, + "loss": 3.5438, + "step": 1111040 + }, + { + "epoch": 0.01, + "learning_rate": 3.180231373533032e-05, + "loss": 3.5277, + "step": 1111552 + }, + { + "epoch": 0.01, + "learning_rate": 3.17939277878198e-05, + "loss": 3.5412, + "step": 1112064 + }, + { + "epoch": 0.01, + "learning_rate": 3.178554184030928e-05, + "loss": 3.5515, + "step": 1112576 + }, + { + "epoch": 0.01, + "learning_rate": 3.17771722716025e-05, + "loss": 3.5463, + "step": 1113088 + }, + { + "epoch": 0.01, + "learning_rate": 3.176878632409198e-05, + "loss": 3.5475, + "step": 1113600 + }, + { + "epoch": 0.01, + "learning_rate": 3.176040037658146e-05, + "loss": 3.5417, + "step": 1114112 + }, + { + "epoch": 0.02, + "learning_rate": 3.175201442907094e-05, + "loss": 3.5374, + "step": 1114624 + }, + { + "epoch": 0.02, + "learning_rate": 3.174364486036415e-05, + "loss": 3.5403, + "step": 1115136 + }, + { + "epoch": 0.02, + "learning_rate": 3.173525891285363e-05, + "loss": 3.5386, + "step": 1115648 + }, + { + "epoch": 0.02, + "learning_rate": 3.172687296534311e-05, + "loss": 3.5516, + "step": 1116160 + }, + { + "epoch": 0.02, + "learning_rate": 3.1718503396636316e-05, + "loss": 3.5506, + "step": 1116672 + }, + { + "epoch": 0.02, + "learning_rate": 3.1710117449125796e-05, + "loss": 3.563, + "step": 1117184 + }, + { + "epoch": 0.02, + "learning_rate": 3.1701731501615276e-05, + "loss": 3.5336, + "step": 1117696 + }, + { + "epoch": 0.02, + "learning_rate": 3.1693345554104756e-05, + "loss": 3.5442, + "step": 1118208 + }, + { + "epoch": 0.02, + "learning_rate": 3.1684959606594236e-05, + "loss": 3.5481, + "step": 1118720 + }, + { + "epoch": 0.02, + "learning_rate": 3.1676573659083716e-05, + "loss": 3.5493, + "step": 1119232 + }, + { + "epoch": 0.02, + "learning_rate": 3.16681877115732e-05, + "loss": 3.5495, + "step": 1119744 + }, + { + "epoch": 0.02, + "learning_rate": 3.165980176406268e-05, + "loss": 3.5475, + "step": 1120256 + }, + { + "epoch": 0.02, + "learning_rate": 3.165143219535589e-05, + "loss": 3.5483, + "step": 1120768 + }, + { + "epoch": 0.02, + "learning_rate": 3.164304624784537e-05, + "loss": 3.5379, + "step": 1121280 + }, + { + "epoch": 0.02, + "learning_rate": 3.163466030033485e-05, + "loss": 3.5514, + "step": 1121792 + }, + { + "epoch": 0.02, + "learning_rate": 3.162627435282433e-05, + "loss": 3.526, + "step": 1122304 + }, + { + "epoch": 0.02, + "learning_rate": 3.161790478411754e-05, + "loss": 3.5367, + "step": 1122816 + }, + { + "epoch": 0.02, + "learning_rate": 3.160951883660702e-05, + "loss": 3.5478, + "step": 1123328 + }, + { + "epoch": 0.02, + "learning_rate": 3.16011328890965e-05, + "loss": 3.5488, + "step": 1123840 + }, + { + "epoch": 0.02, + "learning_rate": 3.159274694158598e-05, + "loss": 3.5356, + "step": 1124352 + }, + { + "epoch": 0.02, + "learning_rate": 3.158437737287919e-05, + "loss": 3.5401, + "step": 1124864 + }, + { + "epoch": 0.02, + "learning_rate": 3.157599142536867e-05, + "loss": 3.5332, + "step": 1125376 + }, + { + "epoch": 0.02, + "learning_rate": 3.1567605477858156e-05, + "loss": 3.5434, + "step": 1125888 + }, + { + "epoch": 0.02, + "learning_rate": 3.1559219530347636e-05, + "loss": 3.5414, + "step": 1126400 + }, + { + "epoch": 0.02, + "learning_rate": 3.1550849961640845e-05, + "loss": 3.551, + "step": 1126912 + }, + { + "epoch": 0.02, + "learning_rate": 3.1542464014130325e-05, + "loss": 3.5536, + "step": 1127424 + }, + { + "epoch": 0.02, + "learning_rate": 3.1534078066619805e-05, + "loss": 3.5568, + "step": 1127936 + }, + { + "epoch": 0.02, + "learning_rate": 3.1525692119109285e-05, + "loss": 3.5361, + "step": 1128448 + }, + { + "epoch": 0.02, + "learning_rate": 3.1517322550402494e-05, + "loss": 3.5432, + "step": 1128960 + }, + { + "epoch": 0.02, + "learning_rate": 3.1508936602891974e-05, + "loss": 3.549, + "step": 1129472 + }, + { + "epoch": 0.02, + "learning_rate": 3.1500550655381454e-05, + "loss": 3.5418, + "step": 1129984 + }, + { + "epoch": 0.02, + "learning_rate": 3.1492164707870934e-05, + "loss": 3.54, + "step": 1130496 + }, + { + "epoch": 0.02, + "learning_rate": 3.1483795139164143e-05, + "loss": 3.5395, + "step": 1131008 + }, + { + "epoch": 0.02, + "learning_rate": 3.147540919165362e-05, + "loss": 3.5416, + "step": 1131520 + }, + { + "epoch": 0.02, + "learning_rate": 3.146702324414311e-05, + "loss": 3.5393, + "step": 1132032 + }, + { + "epoch": 0.02, + "learning_rate": 3.145863729663259e-05, + "loss": 3.534, + "step": 1132544 + }, + { + "epoch": 0.02, + "learning_rate": 3.14502677279258e-05, + "loss": 3.545, + "step": 1133056 + }, + { + "epoch": 0.02, + "learning_rate": 3.144188178041528e-05, + "loss": 3.5404, + "step": 1133568 + }, + { + "epoch": 0.02, + "learning_rate": 3.143349583290476e-05, + "loss": 3.5328, + "step": 1134080 + }, + { + "epoch": 0.02, + "learning_rate": 3.142512626419797e-05, + "loss": 3.5448, + "step": 1134592 + }, + { + "epoch": 0.02, + "learning_rate": 3.141674031668745e-05, + "loss": 3.5457, + "step": 1135104 + }, + { + "epoch": 0.02, + "learning_rate": 3.140835436917693e-05, + "loss": 3.5573, + "step": 1135616 + }, + { + "epoch": 0.02, + "learning_rate": 3.139996842166641e-05, + "loss": 3.5407, + "step": 1136128 + }, + { + "epoch": 0.02, + "learning_rate": 3.139159885295962e-05, + "loss": 3.5417, + "step": 1136640 + }, + { + "epoch": 0.02, + "learning_rate": 3.13832129054491e-05, + "loss": 3.551, + "step": 1137152 + }, + { + "epoch": 0.02, + "learning_rate": 3.137482695793858e-05, + "loss": 3.5387, + "step": 1137664 + }, + { + "epoch": 0.02, + "learning_rate": 3.1366441010428064e-05, + "loss": 3.5456, + "step": 1138176 + }, + { + "epoch": 0.02, + "learning_rate": 3.135807144172127e-05, + "loss": 3.5428, + "step": 1138688 + }, + { + "epoch": 0.02, + "learning_rate": 3.134968549421075e-05, + "loss": 3.5499, + "step": 1139200 + }, + { + "epoch": 0.02, + "learning_rate": 3.134129954670023e-05, + "loss": 3.548, + "step": 1139712 + }, + { + "epoch": 0.02, + "learning_rate": 3.133291359918971e-05, + "loss": 3.5433, + "step": 1140224 + }, + { + "epoch": 0.02, + "learning_rate": 3.132454403048292e-05, + "loss": 3.5403, + "step": 1140736 + }, + { + "epoch": 0.02, + "learning_rate": 3.131617446177613e-05, + "loss": 3.5474, + "step": 1141248 + }, + { + "epoch": 0.02, + "learning_rate": 3.130778851426561e-05, + "loss": 3.5385, + "step": 1141760 + }, + { + "epoch": 0.02, + "learning_rate": 3.129940256675509e-05, + "loss": 3.5389, + "step": 1142272 + }, + { + "epoch": 0.02, + "learning_rate": 3.129101661924457e-05, + "loss": 3.5489, + "step": 1142784 + }, + { + "epoch": 0.02, + "learning_rate": 3.128263067173405e-05, + "loss": 3.538, + "step": 1143296 + }, + { + "epoch": 0.02, + "learning_rate": 3.127424472422353e-05, + "loss": 3.5538, + "step": 1143808 + }, + { + "epoch": 0.02, + "learning_rate": 3.126585877671301e-05, + "loss": 3.5304, + "step": 1144320 + }, + { + "epoch": 0.03, + "eval_loss": 3.842334032058716, + "eval_runtime": 303.5328, + "eval_samples_per_second": 1257.166, + "eval_steps_per_second": 39.287, + "step": 1144800 + }, + { + "epoch": 1.0, + "learning_rate": 3.125747282920249e-05, + "loss": 3.5381, + "step": 1144832 + }, + { + "epoch": 1.0, + "learning_rate": 3.1249103260495706e-05, + "loss": 3.5368, + "step": 1145344 + }, + { + "epoch": 1.0, + "learning_rate": 3.1240717312985186e-05, + "loss": 3.5347, + "step": 1145856 + }, + { + "epoch": 1.0, + "learning_rate": 3.1232331365474666e-05, + "loss": 3.5491, + "step": 1146368 + }, + { + "epoch": 1.0, + "learning_rate": 3.122394541796414e-05, + "loss": 3.548, + "step": 1146880 + }, + { + "epoch": 1.0, + "learning_rate": 3.1215575849257355e-05, + "loss": 3.5464, + "step": 1147392 + }, + { + "epoch": 1.0, + "learning_rate": 3.1207189901746835e-05, + "loss": 3.5362, + "step": 1147904 + }, + { + "epoch": 1.0, + "learning_rate": 3.119880395423631e-05, + "loss": 3.5371, + "step": 1148416 + }, + { + "epoch": 1.0, + "learning_rate": 3.119041800672579e-05, + "loss": 3.5334, + "step": 1148928 + }, + { + "epoch": 1.0, + "learning_rate": 3.1182048438019004e-05, + "loss": 3.5428, + "step": 1149440 + }, + { + "epoch": 1.0, + "learning_rate": 3.1173662490508484e-05, + "loss": 3.5388, + "step": 1149952 + }, + { + "epoch": 1.0, + "learning_rate": 3.1165276542997964e-05, + "loss": 3.5458, + "step": 1150464 + }, + { + "epoch": 1.0, + "learning_rate": 3.1156890595487444e-05, + "loss": 3.5409, + "step": 1150976 + }, + { + "epoch": 1.0, + "learning_rate": 3.114852102678066e-05, + "loss": 3.5311, + "step": 1151488 + }, + { + "epoch": 1.0, + "learning_rate": 3.114013507927014e-05, + "loss": 3.5319, + "step": 1152000 + }, + { + "epoch": 1.0, + "learning_rate": 3.113174913175961e-05, + "loss": 3.5296, + "step": 1152512 + }, + { + "epoch": 1.0, + "learning_rate": 3.112336318424909e-05, + "loss": 3.5403, + "step": 1153024 + }, + { + "epoch": 1.0, + "learning_rate": 3.111499361554231e-05, + "loss": 3.5314, + "step": 1153536 + }, + { + "epoch": 1.0, + "learning_rate": 3.110660766803178e-05, + "loss": 3.5351, + "step": 1154048 + }, + { + "epoch": 1.0, + "learning_rate": 3.109822172052126e-05, + "loss": 3.537, + "step": 1154560 + }, + { + "epoch": 1.0, + "learning_rate": 3.108983577301074e-05, + "loss": 3.5453, + "step": 1155072 + }, + { + "epoch": 1.0, + "learning_rate": 3.108146620430396e-05, + "loss": 3.5443, + "step": 1155584 + }, + { + "epoch": 1.0, + "learning_rate": 3.107308025679344e-05, + "loss": 3.5368, + "step": 1156096 + }, + { + "epoch": 1.0, + "learning_rate": 3.106469430928292e-05, + "loss": 3.5393, + "step": 1156608 + }, + { + "epoch": 1.0, + "learning_rate": 3.10563083617724e-05, + "loss": 3.5451, + "step": 1157120 + }, + { + "epoch": 1.0, + "learning_rate": 3.1047938793065614e-05, + "loss": 3.5389, + "step": 1157632 + }, + { + "epoch": 1.0, + "learning_rate": 3.103955284555509e-05, + "loss": 3.5302, + "step": 1158144 + }, + { + "epoch": 1.0, + "learning_rate": 3.103116689804457e-05, + "loss": 3.5414, + "step": 1158656 + }, + { + "epoch": 1.0, + "learning_rate": 3.102278095053405e-05, + "loss": 3.5243, + "step": 1159168 + }, + { + "epoch": 1.0, + "learning_rate": 3.1014411381827256e-05, + "loss": 3.5287, + "step": 1159680 + }, + { + "epoch": 1.01, + "learning_rate": 3.1006025434316736e-05, + "loss": 3.5317, + "step": 1160192 + }, + { + "epoch": 1.01, + "learning_rate": 3.0997639486806216e-05, + "loss": 3.535, + "step": 1160704 + }, + { + "epoch": 1.01, + "learning_rate": 3.098926991809943e-05, + "loss": 3.5449, + "step": 1161216 + }, + { + "epoch": 1.01, + "learning_rate": 3.098088397058891e-05, + "loss": 3.5418, + "step": 1161728 + }, + { + "epoch": 1.01, + "learning_rate": 3.097249802307839e-05, + "loss": 3.5358, + "step": 1162240 + }, + { + "epoch": 1.01, + "learning_rate": 3.096411207556787e-05, + "loss": 3.5407, + "step": 1162752 + }, + { + "epoch": 1.01, + "learning_rate": 3.095574250686109e-05, + "loss": 3.548, + "step": 1163264 + }, + { + "epoch": 1.01, + "learning_rate": 3.094735655935056e-05, + "loss": 3.5275, + "step": 1163776 + }, + { + "epoch": 1.01, + "learning_rate": 3.093897061184004e-05, + "loss": 3.535, + "step": 1164288 + }, + { + "epoch": 1.01, + "learning_rate": 3.093058466432952e-05, + "loss": 3.5238, + "step": 1164800 + }, + { + "epoch": 1.01, + "learning_rate": 3.092221509562273e-05, + "loss": 3.5318, + "step": 1165312 + }, + { + "epoch": 1.01, + "learning_rate": 3.091382914811221e-05, + "loss": 3.5341, + "step": 1165824 + }, + { + "epoch": 1.01, + "learning_rate": 3.090544320060169e-05, + "loss": 3.54, + "step": 1166336 + }, + { + "epoch": 1.01, + "learning_rate": 3.089705725309117e-05, + "loss": 3.5317, + "step": 1166848 + }, + { + "epoch": 1.01, + "learning_rate": 3.088868768438438e-05, + "loss": 3.5291, + "step": 1167360 + }, + { + "epoch": 1.01, + "learning_rate": 3.0880301736873865e-05, + "loss": 3.5401, + "step": 1167872 + }, + { + "epoch": 1.01, + "learning_rate": 3.0871915789363345e-05, + "loss": 3.5297, + "step": 1168384 + }, + { + "epoch": 1.01, + "learning_rate": 3.0863529841852825e-05, + "loss": 3.5274, + "step": 1168896 + }, + { + "epoch": 1.01, + "learning_rate": 3.0855160273146034e-05, + "loss": 3.5091, + "step": 1169408 + }, + { + "epoch": 1.01, + "learning_rate": 3.0846774325635514e-05, + "loss": 3.5407, + "step": 1169920 + }, + { + "epoch": 1.01, + "learning_rate": 3.0838388378124994e-05, + "loss": 3.533, + "step": 1170432 + }, + { + "epoch": 1.01, + "learning_rate": 3.0830002430614474e-05, + "loss": 3.5379, + "step": 1170944 + }, + { + "epoch": 1.01, + "learning_rate": 3.082163286190768e-05, + "loss": 3.5308, + "step": 1171456 + }, + { + "epoch": 1.01, + "learning_rate": 3.081324691439716e-05, + "loss": 3.5243, + "step": 1171968 + }, + { + "epoch": 1.01, + "learning_rate": 3.080486096688664e-05, + "loss": 3.5202, + "step": 1172480 + }, + { + "epoch": 1.01, + "learning_rate": 3.079647501937612e-05, + "loss": 3.5226, + "step": 1172992 + }, + { + "epoch": 1.01, + "learning_rate": 3.078810545066933e-05, + "loss": 3.5367, + "step": 1173504 + }, + { + "epoch": 1.01, + "learning_rate": 3.077971950315882e-05, + "loss": 3.5239, + "step": 1174016 + }, + { + "epoch": 1.01, + "learning_rate": 3.07713335556483e-05, + "loss": 3.537, + "step": 1174528 + }, + { + "epoch": 1.01, + "learning_rate": 3.076294760813778e-05, + "loss": 3.5308, + "step": 1175040 + }, + { + "epoch": 1.01, + "learning_rate": 3.075457803943099e-05, + "loss": 3.5222, + "step": 1175552 + }, + { + "epoch": 1.01, + "learning_rate": 3.074619209192047e-05, + "loss": 3.534, + "step": 1176064 + }, + { + "epoch": 1.01, + "learning_rate": 3.073780614440995e-05, + "loss": 3.5261, + "step": 1176576 + }, + { + "epoch": 1.01, + "learning_rate": 3.072942019689943e-05, + "loss": 3.5254, + "step": 1177088 + }, + { + "epoch": 1.01, + "learning_rate": 3.072105062819264e-05, + "loss": 3.5224, + "step": 1177600 + }, + { + "epoch": 1.01, + "learning_rate": 3.071266468068212e-05, + "loss": 3.5379, + "step": 1178112 + }, + { + "epoch": 1.01, + "learning_rate": 3.07042787331716e-05, + "loss": 3.5247, + "step": 1178624 + }, + { + "epoch": 1.01, + "learning_rate": 3.069589278566108e-05, + "loss": 3.5281, + "step": 1179136 + }, + { + "epoch": 1.01, + "learning_rate": 3.0687523216954286e-05, + "loss": 3.5181, + "step": 1179648 + }, + { + "epoch": 1.01, + "learning_rate": 3.067913726944377e-05, + "loss": 3.5259, + "step": 1180160 + }, + { + "epoch": 1.01, + "learning_rate": 3.067075132193325e-05, + "loss": 3.5274, + "step": 1180672 + }, + { + "epoch": 1.01, + "learning_rate": 3.066236537442273e-05, + "loss": 3.5398, + "step": 1181184 + }, + { + "epoch": 1.01, + "learning_rate": 3.065399580571594e-05, + "loss": 3.5307, + "step": 1181696 + }, + { + "epoch": 1.01, + "learning_rate": 3.064560985820542e-05, + "loss": 3.5355, + "step": 1182208 + }, + { + "epoch": 1.01, + "learning_rate": 3.06372239106949e-05, + "loss": 3.5417, + "step": 1182720 + }, + { + "epoch": 1.01, + "learning_rate": 3.062883796318438e-05, + "loss": 3.5325, + "step": 1183232 + }, + { + "epoch": 1.01, + "learning_rate": 3.062046839447759e-05, + "loss": 3.5317, + "step": 1183744 + }, + { + "epoch": 1.01, + "learning_rate": 3.061208244696707e-05, + "loss": 3.5347, + "step": 1184256 + }, + { + "epoch": 1.01, + "learning_rate": 3.060369649945655e-05, + "loss": 3.5348, + "step": 1184768 + }, + { + "epoch": 1.01, + "learning_rate": 3.059532693074976e-05, + "loss": 3.5304, + "step": 1185280 + }, + { + "epoch": 1.01, + "learning_rate": 3.058694098323924e-05, + "loss": 3.531, + "step": 1185792 + }, + { + "epoch": 1.01, + "learning_rate": 3.0578555035728726e-05, + "loss": 3.5412, + "step": 1186304 + }, + { + "epoch": 1.01, + "learning_rate": 3.0570169088218206e-05, + "loss": 3.5418, + "step": 1186816 + }, + { + "epoch": 1.01, + "learning_rate": 3.0561783140707686e-05, + "loss": 3.5276, + "step": 1187328 + }, + { + "epoch": 1.01, + "learning_rate": 3.0553397193197166e-05, + "loss": 3.5122, + "step": 1187840 + }, + { + "epoch": 1.01, + "learning_rate": 3.0545011245686646e-05, + "loss": 3.5243, + "step": 1188352 + }, + { + "epoch": 1.01, + "learning_rate": 3.0536625298176126e-05, + "loss": 3.5371, + "step": 1188864 + }, + { + "epoch": 1.01, + "learning_rate": 3.0528255729469335e-05, + "loss": 3.532, + "step": 1189376 + }, + { + "epoch": 1.01, + "learning_rate": 3.0519869781958815e-05, + "loss": 3.5347, + "step": 1189888 + }, + { + "epoch": 1.01, + "learning_rate": 3.0511483834448295e-05, + "loss": 3.5302, + "step": 1190400 + }, + { + "epoch": 1.02, + "learning_rate": 3.0503097886937775e-05, + "loss": 3.5239, + "step": 1190912 + }, + { + "epoch": 1.02, + "learning_rate": 3.0494728318230988e-05, + "loss": 3.5216, + "step": 1191424 + }, + { + "epoch": 1.02, + "learning_rate": 3.0486342370720468e-05, + "loss": 3.5237, + "step": 1191936 + }, + { + "epoch": 1.02, + "learning_rate": 3.0477956423209948e-05, + "loss": 3.5352, + "step": 1192448 + }, + { + "epoch": 1.02, + "learning_rate": 3.0469570475699427e-05, + "loss": 3.5339, + "step": 1192960 + }, + { + "epoch": 1.02, + "learning_rate": 3.0461200906992637e-05, + "loss": 3.5484, + "step": 1193472 + }, + { + "epoch": 1.02, + "learning_rate": 3.0452814959482117e-05, + "loss": 3.5224, + "step": 1193984 + }, + { + "epoch": 1.02, + "learning_rate": 3.0444429011971596e-05, + "loss": 3.5287, + "step": 1194496 + }, + { + "epoch": 1.02, + "learning_rate": 3.043604306446108e-05, + "loss": 3.531, + "step": 1195008 + }, + { + "epoch": 1.02, + "learning_rate": 3.042767349575429e-05, + "loss": 3.5342, + "step": 1195520 + }, + { + "epoch": 1.02, + "learning_rate": 3.041928754824377e-05, + "loss": 3.5337, + "step": 1196032 + }, + { + "epoch": 1.02, + "learning_rate": 3.041090160073325e-05, + "loss": 3.5314, + "step": 1196544 + }, + { + "epoch": 1.02, + "learning_rate": 3.040251565322273e-05, + "loss": 3.5322, + "step": 1197056 + }, + { + "epoch": 1.02, + "learning_rate": 3.039414608451594e-05, + "loss": 3.5217, + "step": 1197568 + }, + { + "epoch": 1.02, + "learning_rate": 3.038576013700542e-05, + "loss": 3.5402, + "step": 1198080 + }, + { + "epoch": 1.02, + "learning_rate": 3.03773741894949e-05, + "loss": 3.5129, + "step": 1198592 + }, + { + "epoch": 1.02, + "learning_rate": 3.036898824198438e-05, + "loss": 3.5229, + "step": 1199104 + }, + { + "epoch": 1.02, + "learning_rate": 3.036061867327759e-05, + "loss": 3.532, + "step": 1199616 + }, + { + "epoch": 1.02, + "learning_rate": 3.035223272576707e-05, + "loss": 3.5293, + "step": 1200128 + }, + { + "epoch": 1.02, + "learning_rate": 3.034384677825655e-05, + "loss": 3.5184, + "step": 1200640 + }, + { + "epoch": 1.02, + "learning_rate": 3.0335460830746034e-05, + "loss": 3.5316, + "step": 1201152 + }, + { + "epoch": 1.02, + "learning_rate": 3.0327091262039243e-05, + "loss": 3.5147, + "step": 1201664 + }, + { + "epoch": 1.02, + "learning_rate": 3.0318705314528723e-05, + "loss": 3.5317, + "step": 1202176 + }, + { + "epoch": 1.02, + "learning_rate": 3.0310319367018203e-05, + "loss": 3.5274, + "step": 1202688 + }, + { + "epoch": 1.02, + "learning_rate": 3.030194979831141e-05, + "loss": 3.5346, + "step": 1203200 + }, + { + "epoch": 1.02, + "learning_rate": 3.0293563850800895e-05, + "loss": 3.5378, + "step": 1203712 + }, + { + "epoch": 1.02, + "learning_rate": 3.0285177903290375e-05, + "loss": 3.5398, + "step": 1204224 + }, + { + "epoch": 1.02, + "learning_rate": 3.0276791955779855e-05, + "loss": 3.5247, + "step": 1204736 + }, + { + "epoch": 1.02, + "learning_rate": 3.0268422387073064e-05, + "loss": 3.5311, + "step": 1205248 + }, + { + "epoch": 1.02, + "learning_rate": 3.0260036439562544e-05, + "loss": 3.5325, + "step": 1205760 + }, + { + "epoch": 1.02, + "learning_rate": 3.0251650492052024e-05, + "loss": 3.5239, + "step": 1206272 + }, + { + "epoch": 1.02, + "learning_rate": 3.0243264544541504e-05, + "loss": 3.529, + "step": 1206784 + }, + { + "epoch": 1.02, + "learning_rate": 3.0234894975834716e-05, + "loss": 3.523, + "step": 1207296 + }, + { + "epoch": 1.02, + "learning_rate": 3.0226509028324196e-05, + "loss": 3.5282, + "step": 1207808 + }, + { + "epoch": 1.02, + "learning_rate": 3.0218123080813676e-05, + "loss": 3.5247, + "step": 1208320 + }, + { + "epoch": 1.02, + "learning_rate": 3.0209737133303156e-05, + "loss": 3.5221, + "step": 1208832 + }, + { + "epoch": 1.02, + "learning_rate": 3.0201367564596365e-05, + "loss": 3.5285, + "step": 1209344 + }, + { + "epoch": 1.02, + "learning_rate": 3.019298161708585e-05, + "loss": 3.5241, + "step": 1209856 + }, + { + "epoch": 1.02, + "learning_rate": 3.018459566957533e-05, + "loss": 3.5233, + "step": 1210368 + }, + { + "epoch": 1.02, + "learning_rate": 3.017620972206481e-05, + "loss": 3.5265, + "step": 1210880 + }, + { + "epoch": 1.02, + "learning_rate": 3.0167840153358018e-05, + "loss": 3.5335, + "step": 1211392 + }, + { + "epoch": 1.02, + "learning_rate": 3.0159454205847498e-05, + "loss": 3.5454, + "step": 1211904 + }, + { + "epoch": 1.02, + "learning_rate": 3.0151068258336978e-05, + "loss": 3.5215, + "step": 1212416 + }, + { + "epoch": 1.02, + "learning_rate": 3.0142682310826457e-05, + "loss": 3.5258, + "step": 1212928 + }, + { + "epoch": 1.02, + "learning_rate": 3.013431274211967e-05, + "loss": 3.5359, + "step": 1213440 + }, + { + "epoch": 1.02, + "learning_rate": 3.012592679460915e-05, + "loss": 3.5277, + "step": 1213952 + }, + { + "epoch": 1.02, + "learning_rate": 3.011754084709863e-05, + "loss": 3.531, + "step": 1214464 + }, + { + "epoch": 1.02, + "learning_rate": 3.0109154899588103e-05, + "loss": 3.5277, + "step": 1214976 + }, + { + "epoch": 1.02, + "learning_rate": 3.010078533088132e-05, + "loss": 3.5348, + "step": 1215488 + }, + { + "epoch": 1.02, + "learning_rate": 3.0092399383370802e-05, + "loss": 3.5281, + "step": 1216000 + }, + { + "epoch": 1.02, + "learning_rate": 3.0084013435860282e-05, + "loss": 3.5324, + "step": 1216512 + }, + { + "epoch": 1.02, + "learning_rate": 3.0075627488349755e-05, + "loss": 3.5265, + "step": 1217024 + }, + { + "epoch": 1.02, + "learning_rate": 3.00672742984467e-05, + "loss": 3.5269, + "step": 1217536 + }, + { + "epoch": 1.02, + "learning_rate": 3.005888835093618e-05, + "loss": 3.5254, + "step": 1218048 + }, + { + "epoch": 1.02, + "learning_rate": 3.0050502403425664e-05, + "loss": 3.5242, + "step": 1218560 + }, + { + "epoch": 1.02, + "learning_rate": 3.0042116455915144e-05, + "loss": 3.5349, + "step": 1219072 + }, + { + "epoch": 1.02, + "learning_rate": 3.0033730508404624e-05, + "loss": 3.5238, + "step": 1219584 + }, + { + "epoch": 1.02, + "learning_rate": 3.0025344560894104e-05, + "loss": 3.5396, + "step": 1220096 + }, + { + "epoch": 1.02, + "learning_rate": 3.0016958613383577e-05, + "loss": 3.5159, + "step": 1220608 + }, + { + "epoch": 1.03, + "learning_rate": 3.0008572665873057e-05, + "loss": 3.5273, + "step": 1221120 + }, + { + "epoch": 1.03, + "eval_loss": 3.8431098461151123, + "eval_runtime": 303.5721, + "eval_samples_per_second": 1257.003, + "eval_steps_per_second": 39.282, + "step": 1221120 + }, + { + "epoch": 0.0, + "learning_rate": 3.000018671836254e-05, + "loss": 3.5187, + "step": 1221632 + }, + { + "epoch": 0.0, + "learning_rate": 2.999180077085202e-05, + "loss": 3.5198, + "step": 1222144 + }, + { + "epoch": 0.0, + "learning_rate": 2.99834148233415e-05, + "loss": 3.5349, + "step": 1222656 + }, + { + "epoch": 0.0, + "learning_rate": 2.997504525463471e-05, + "loss": 3.5331, + "step": 1223168 + }, + { + "epoch": 0.0, + "learning_rate": 2.996665930712419e-05, + "loss": 3.5359, + "step": 1223680 + }, + { + "epoch": 0.0, + "learning_rate": 2.9958289738417405e-05, + "loss": 3.5208, + "step": 1224192 + }, + { + "epoch": 0.0, + "learning_rate": 2.994990379090688e-05, + "loss": 3.5223, + "step": 1224704 + }, + { + "epoch": 0.0, + "learning_rate": 2.994151784339636e-05, + "loss": 3.513, + "step": 1225216 + }, + { + "epoch": 0.0, + "learning_rate": 2.993313189588584e-05, + "loss": 3.5341, + "step": 1225728 + }, + { + "epoch": 0.0, + "learning_rate": 2.992474594837532e-05, + "loss": 3.5197, + "step": 1226240 + }, + { + "epoch": 0.0, + "learning_rate": 2.99163600008648e-05, + "loss": 3.5345, + "step": 1226752 + }, + { + "epoch": 0.0, + "learning_rate": 2.990797405335428e-05, + "loss": 3.5248, + "step": 1227264 + }, + { + "epoch": 0.0, + "learning_rate": 2.989958810584376e-05, + "loss": 3.5186, + "step": 1227776 + }, + { + "epoch": 0.0, + "learning_rate": 2.9891218537136974e-05, + "loss": 3.5159, + "step": 1228288 + }, + { + "epoch": 0.0, + "learning_rate": 2.9882832589626454e-05, + "loss": 3.5161, + "step": 1228800 + }, + { + "epoch": 0.0, + "learning_rate": 2.9874446642115934e-05, + "loss": 3.5214, + "step": 1229312 + }, + { + "epoch": 0.0, + "learning_rate": 2.9866060694605414e-05, + "loss": 3.5196, + "step": 1229824 + }, + { + "epoch": 0.0, + "learning_rate": 2.9857691125898623e-05, + "loss": 3.5197, + "step": 1230336 + }, + { + "epoch": 0.0, + "learning_rate": 2.9849305178388103e-05, + "loss": 3.5201, + "step": 1230848 + }, + { + "epoch": 0.0, + "learning_rate": 2.9840919230877583e-05, + "loss": 3.5337, + "step": 1231360 + }, + { + "epoch": 0.0, + "learning_rate": 2.9832533283367066e-05, + "loss": 3.5248, + "step": 1231872 + }, + { + "epoch": 0.0, + "learning_rate": 2.9824163714660275e-05, + "loss": 3.5272, + "step": 1232384 + }, + { + "epoch": 0.0, + "learning_rate": 2.9815777767149755e-05, + "loss": 3.519, + "step": 1232896 + }, + { + "epoch": 0.0, + "learning_rate": 2.9807391819639235e-05, + "loss": 3.5313, + "step": 1233408 + }, + { + "epoch": 0.0, + "learning_rate": 2.9799005872128715e-05, + "loss": 3.5212, + "step": 1233920 + }, + { + "epoch": 0.0, + "learning_rate": 2.9790636303421927e-05, + "loss": 3.5194, + "step": 1234432 + }, + { + "epoch": 0.0, + "learning_rate": 2.9782250355911407e-05, + "loss": 3.5259, + "step": 1234944 + }, + { + "epoch": 0.0, + "learning_rate": 2.9773880787204616e-05, + "loss": 3.5086, + "step": 1235456 + }, + { + "epoch": 0.0, + "learning_rate": 2.9765494839694096e-05, + "loss": 3.5147, + "step": 1235968 + }, + { + "epoch": 0.01, + "learning_rate": 2.9757108892183576e-05, + "loss": 3.5139, + "step": 1236480 + }, + { + "epoch": 0.01, + "learning_rate": 2.9748722944673056e-05, + "loss": 3.5243, + "step": 1236992 + }, + { + "epoch": 0.01, + "learning_rate": 2.9740336997162536e-05, + "loss": 3.5251, + "step": 1237504 + }, + { + "epoch": 0.01, + "learning_rate": 2.973195104965202e-05, + "loss": 3.5283, + "step": 1238016 + }, + { + "epoch": 0.01, + "learning_rate": 2.97235651021415e-05, + "loss": 3.5249, + "step": 1238528 + }, + { + "epoch": 0.01, + "learning_rate": 2.971517915463098e-05, + "loss": 3.5239, + "step": 1239040 + }, + { + "epoch": 0.01, + "learning_rate": 2.970680958592419e-05, + "loss": 3.5328, + "step": 1239552 + }, + { + "epoch": 0.01, + "learning_rate": 2.9698440017217398e-05, + "loss": 3.5128, + "step": 1240064 + }, + { + "epoch": 0.01, + "learning_rate": 2.969005406970688e-05, + "loss": 3.5224, + "step": 1240576 + }, + { + "epoch": 0.01, + "learning_rate": 2.968166812219636e-05, + "loss": 3.5055, + "step": 1241088 + }, + { + "epoch": 0.01, + "learning_rate": 2.967328217468584e-05, + "loss": 3.5233, + "step": 1241600 + }, + { + "epoch": 0.01, + "learning_rate": 2.966489622717532e-05, + "loss": 3.5145, + "step": 1242112 + }, + { + "epoch": 0.01, + "learning_rate": 2.96565102796648e-05, + "loss": 3.5264, + "step": 1242624 + }, + { + "epoch": 0.01, + "learning_rate": 2.964812433215428e-05, + "loss": 3.5171, + "step": 1243136 + }, + { + "epoch": 0.01, + "learning_rate": 2.963975476344749e-05, + "loss": 3.5174, + "step": 1243648 + }, + { + "epoch": 0.01, + "learning_rate": 2.9631368815936973e-05, + "loss": 3.526, + "step": 1244160 + }, + { + "epoch": 0.01, + "learning_rate": 2.9622982868426453e-05, + "loss": 3.5172, + "step": 1244672 + }, + { + "epoch": 0.01, + "learning_rate": 2.9614596920915933e-05, + "loss": 3.5131, + "step": 1245184 + }, + { + "epoch": 0.01, + "learning_rate": 2.9606227352209142e-05, + "loss": 3.4978, + "step": 1245696 + }, + { + "epoch": 0.01, + "learning_rate": 2.9597841404698622e-05, + "loss": 3.5208, + "step": 1246208 + }, + { + "epoch": 0.01, + "learning_rate": 2.9589455457188102e-05, + "loss": 3.5226, + "step": 1246720 + }, + { + "epoch": 0.01, + "learning_rate": 2.9581069509677582e-05, + "loss": 3.5216, + "step": 1247232 + }, + { + "epoch": 0.01, + "learning_rate": 2.9572699940970795e-05, + "loss": 3.513, + "step": 1247744 + }, + { + "epoch": 0.01, + "learning_rate": 2.9564313993460275e-05, + "loss": 3.5093, + "step": 1248256 + }, + { + "epoch": 0.01, + "learning_rate": 2.9555928045949755e-05, + "loss": 3.5082, + "step": 1248768 + }, + { + "epoch": 0.01, + "learning_rate": 2.9547542098439234e-05, + "loss": 3.5061, + "step": 1249280 + }, + { + "epoch": 0.01, + "learning_rate": 2.9539172529732444e-05, + "loss": 3.5308, + "step": 1249792 + }, + { + "epoch": 0.01, + "learning_rate": 2.9530786582221927e-05, + "loss": 3.5057, + "step": 1250304 + }, + { + "epoch": 0.01, + "learning_rate": 2.9522400634711407e-05, + "loss": 3.5237, + "step": 1250816 + }, + { + "epoch": 0.01, + "learning_rate": 2.9514014687200887e-05, + "loss": 3.5192, + "step": 1251328 + }, + { + "epoch": 0.01, + "learning_rate": 2.9505645118494096e-05, + "loss": 3.503, + "step": 1251840 + }, + { + "epoch": 0.01, + "learning_rate": 2.9497259170983576e-05, + "loss": 3.5206, + "step": 1252352 + }, + { + "epoch": 0.01, + "learning_rate": 2.9488873223473056e-05, + "loss": 3.5107, + "step": 1252864 + }, + { + "epoch": 0.01, + "learning_rate": 2.9480487275962536e-05, + "loss": 3.5135, + "step": 1253376 + }, + { + "epoch": 0.01, + "learning_rate": 2.9472117707255748e-05, + "loss": 3.5109, + "step": 1253888 + }, + { + "epoch": 0.01, + "learning_rate": 2.9463731759745228e-05, + "loss": 3.5238, + "step": 1254400 + }, + { + "epoch": 0.01, + "learning_rate": 2.9455345812234708e-05, + "loss": 3.512, + "step": 1254912 + }, + { + "epoch": 0.01, + "learning_rate": 2.944695986472418e-05, + "loss": 3.5074, + "step": 1255424 + }, + { + "epoch": 0.01, + "learning_rate": 2.9438590296017397e-05, + "loss": 3.509, + "step": 1255936 + }, + { + "epoch": 0.01, + "learning_rate": 2.943020434850688e-05, + "loss": 3.5091, + "step": 1256448 + }, + { + "epoch": 0.01, + "learning_rate": 2.942181840099636e-05, + "loss": 3.511, + "step": 1256960 + }, + { + "epoch": 0.01, + "learning_rate": 2.9413432453485834e-05, + "loss": 3.5251, + "step": 1257472 + }, + { + "epoch": 0.01, + "learning_rate": 2.940506288477905e-05, + "loss": 3.5134, + "step": 1257984 + }, + { + "epoch": 0.01, + "learning_rate": 2.939669331607226e-05, + "loss": 3.5222, + "step": 1258496 + }, + { + "epoch": 0.01, + "learning_rate": 2.9388307368561742e-05, + "loss": 3.5275, + "step": 1259008 + }, + { + "epoch": 0.01, + "learning_rate": 2.9379921421051222e-05, + "loss": 3.5207, + "step": 1259520 + }, + { + "epoch": 0.01, + "learning_rate": 2.9371535473540702e-05, + "loss": 3.5164, + "step": 1260032 + }, + { + "epoch": 0.01, + "learning_rate": 2.9363149526030182e-05, + "loss": 3.5191, + "step": 1260544 + }, + { + "epoch": 0.01, + "learning_rate": 2.9354763578519655e-05, + "loss": 3.5225, + "step": 1261056 + }, + { + "epoch": 0.01, + "learning_rate": 2.934639400981287e-05, + "loss": 3.5172, + "step": 1261568 + }, + { + "epoch": 0.01, + "learning_rate": 2.933800806230235e-05, + "loss": 3.5142, + "step": 1262080 + }, + { + "epoch": 0.01, + "learning_rate": 2.9329622114791834e-05, + "loss": 3.5288, + "step": 1262592 + }, + { + "epoch": 0.01, + "learning_rate": 2.9321236167281307e-05, + "loss": 3.5266, + "step": 1263104 + }, + { + "epoch": 0.01, + "learning_rate": 2.9312850219770787e-05, + "loss": 3.513, + "step": 1263616 + }, + { + "epoch": 0.01, + "learning_rate": 2.9304464272260267e-05, + "loss": 3.4981, + "step": 1264128 + }, + { + "epoch": 0.01, + "learning_rate": 2.9296078324749747e-05, + "loss": 3.5112, + "step": 1264640 + }, + { + "epoch": 0.01, + "learning_rate": 2.9287692377239227e-05, + "loss": 3.5242, + "step": 1265152 + }, + { + "epoch": 0.01, + "learning_rate": 2.927932280853244e-05, + "loss": 3.5147, + "step": 1265664 + }, + { + "epoch": 0.01, + "learning_rate": 2.927093686102192e-05, + "loss": 3.5234, + "step": 1266176 + }, + { + "epoch": 0.01, + "learning_rate": 2.92625509135114e-05, + "loss": 3.5102, + "step": 1266688 + }, + { + "epoch": 0.02, + "learning_rate": 2.925416496600088e-05, + "loss": 3.5143, + "step": 1267200 + }, + { + "epoch": 0.02, + "learning_rate": 2.924579539729409e-05, + "loss": 3.5093, + "step": 1267712 + }, + { + "epoch": 0.02, + "learning_rate": 2.9237409449783572e-05, + "loss": 3.5081, + "step": 1268224 + }, + { + "epoch": 0.02, + "learning_rate": 2.9229023502273052e-05, + "loss": 3.5212, + "step": 1268736 + }, + { + "epoch": 0.02, + "learning_rate": 2.922065393356626e-05, + "loss": 3.5174, + "step": 1269248 + }, + { + "epoch": 0.02, + "learning_rate": 2.921226798605574e-05, + "loss": 3.5317, + "step": 1269760 + }, + { + "epoch": 0.02, + "learning_rate": 2.920388203854522e-05, + "loss": 3.5178, + "step": 1270272 + }, + { + "epoch": 0.02, + "learning_rate": 2.91954960910347e-05, + "loss": 3.5121, + "step": 1270784 + }, + { + "epoch": 0.02, + "learning_rate": 2.918711014352418e-05, + "loss": 3.518, + "step": 1271296 + }, + { + "epoch": 0.02, + "learning_rate": 2.9178724196013664e-05, + "loss": 3.5218, + "step": 1271808 + }, + { + "epoch": 0.02, + "learning_rate": 2.9170338248503144e-05, + "loss": 3.5174, + "step": 1272320 + }, + { + "epoch": 0.02, + "learning_rate": 2.9161952300992624e-05, + "loss": 3.5209, + "step": 1272832 + }, + { + "epoch": 0.02, + "learning_rate": 2.9153582732285833e-05, + "loss": 3.5155, + "step": 1273344 + }, + { + "epoch": 0.02, + "learning_rate": 2.9145196784775313e-05, + "loss": 3.5119, + "step": 1273856 + }, + { + "epoch": 0.02, + "learning_rate": 2.9136810837264793e-05, + "loss": 3.5216, + "step": 1274368 + }, + { + "epoch": 0.02, + "learning_rate": 2.9128424889754273e-05, + "loss": 3.5015, + "step": 1274880 + }, + { + "epoch": 0.02, + "learning_rate": 2.9120055321047486e-05, + "loss": 3.509, + "step": 1275392 + }, + { + "epoch": 0.02, + "learning_rate": 2.9111669373536966e-05, + "loss": 3.5186, + "step": 1275904 + }, + { + "epoch": 0.02, + "learning_rate": 2.9103283426026446e-05, + "loss": 3.5128, + "step": 1276416 + }, + { + "epoch": 0.02, + "learning_rate": 2.9094897478515925e-05, + "loss": 3.5044, + "step": 1276928 + }, + { + "epoch": 0.02, + "learning_rate": 2.9086527909809135e-05, + "loss": 3.5217, + "step": 1277440 + }, + { + "epoch": 0.02, + "learning_rate": 2.9078141962298615e-05, + "loss": 3.5019, + "step": 1277952 + }, + { + "epoch": 0.02, + "learning_rate": 2.9069756014788098e-05, + "loss": 3.5147, + "step": 1278464 + }, + { + "epoch": 0.02, + "learning_rate": 2.9061370067277578e-05, + "loss": 3.5123, + "step": 1278976 + }, + { + "epoch": 0.02, + "learning_rate": 2.9053000498570787e-05, + "loss": 3.5203, + "step": 1279488 + }, + { + "epoch": 0.02, + "learning_rate": 2.9044614551060267e-05, + "loss": 3.5276, + "step": 1280000 + }, + { + "epoch": 0.02, + "learning_rate": 2.9036228603549747e-05, + "loss": 3.5249, + "step": 1280512 + }, + { + "epoch": 0.02, + "learning_rate": 2.9027842656039227e-05, + "loss": 3.51, + "step": 1281024 + }, + { + "epoch": 0.02, + "learning_rate": 2.901947308733244e-05, + "loss": 3.516, + "step": 1281536 + }, + { + "epoch": 0.02, + "learning_rate": 2.901108713982192e-05, + "loss": 3.519, + "step": 1282048 + }, + { + "epoch": 0.02, + "learning_rate": 2.90027011923114e-05, + "loss": 3.5101, + "step": 1282560 + }, + { + "epoch": 0.02, + "learning_rate": 2.899431524480088e-05, + "loss": 3.5114, + "step": 1283072 + }, + { + "epoch": 0.02, + "learning_rate": 2.8985945676094088e-05, + "loss": 3.5105, + "step": 1283584 + }, + { + "epoch": 0.02, + "learning_rate": 2.8977559728583568e-05, + "loss": 3.512, + "step": 1284096 + }, + { + "epoch": 0.02, + "learning_rate": 2.896917378107305e-05, + "loss": 3.5138, + "step": 1284608 + }, + { + "epoch": 0.02, + "learning_rate": 2.896078783356253e-05, + "loss": 3.507, + "step": 1285120 + }, + { + "epoch": 0.02, + "learning_rate": 2.895241826485574e-05, + "loss": 3.5141, + "step": 1285632 + }, + { + "epoch": 0.02, + "learning_rate": 2.894403231734522e-05, + "loss": 3.5113, + "step": 1286144 + }, + { + "epoch": 0.02, + "learning_rate": 2.89356463698347e-05, + "loss": 3.5079, + "step": 1286656 + }, + { + "epoch": 0.02, + "learning_rate": 2.892726042232418e-05, + "loss": 3.5074, + "step": 1287168 + }, + { + "epoch": 0.02, + "learning_rate": 2.8918890853617393e-05, + "loss": 3.5232, + "step": 1287680 + }, + { + "epoch": 0.02, + "learning_rate": 2.8910504906106873e-05, + "loss": 3.5294, + "step": 1288192 + }, + { + "epoch": 0.02, + "learning_rate": 2.8902118958596353e-05, + "loss": 3.5152, + "step": 1288704 + }, + { + "epoch": 0.02, + "learning_rate": 2.8893749389889562e-05, + "loss": 3.5063, + "step": 1289216 + }, + { + "epoch": 0.02, + "learning_rate": 2.8885363442379042e-05, + "loss": 3.5159, + "step": 1289728 + }, + { + "epoch": 0.02, + "learning_rate": 2.8876977494868522e-05, + "loss": 3.5183, + "step": 1290240 + }, + { + "epoch": 0.02, + "learning_rate": 2.8868591547358005e-05, + "loss": 3.518, + "step": 1290752 + }, + { + "epoch": 0.02, + "learning_rate": 2.8860221978651214e-05, + "loss": 3.5169, + "step": 1291264 + }, + { + "epoch": 0.02, + "learning_rate": 2.8851836031140694e-05, + "loss": 3.5239, + "step": 1291776 + }, + { + "epoch": 0.02, + "learning_rate": 2.8843450083630174e-05, + "loss": 3.5126, + "step": 1292288 + }, + { + "epoch": 0.02, + "learning_rate": 2.8835064136119654e-05, + "loss": 3.5179, + "step": 1292800 + }, + { + "epoch": 0.02, + "learning_rate": 2.8826694567412867e-05, + "loss": 3.512, + "step": 1293312 + }, + { + "epoch": 0.02, + "learning_rate": 2.8818324998706076e-05, + "loss": 3.5162, + "step": 1293824 + }, + { + "epoch": 0.02, + "learning_rate": 2.8809939051195556e-05, + "loss": 3.5093, + "step": 1294336 + }, + { + "epoch": 0.02, + "learning_rate": 2.8801553103685036e-05, + "loss": 3.5093, + "step": 1294848 + }, + { + "epoch": 0.02, + "learning_rate": 2.8793167156174516e-05, + "loss": 3.5247, + "step": 1295360 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784781208663996e-05, + "loss": 3.5113, + "step": 1295872 + }, + { + "epoch": 0.02, + "learning_rate": 2.8776395261153476e-05, + "loss": 3.5233, + "step": 1296384 + }, + { + "epoch": 0.02, + "learning_rate": 2.876800931364296e-05, + "loss": 3.506, + "step": 1296896 + }, + { + "epoch": 0.02, + "learning_rate": 2.875962336613244e-05, + "loss": 3.5084, + "step": 1297408 + }, + { + "epoch": 0.03, + "eval_loss": 3.843625783920288, + "eval_runtime": 517.9384, + "eval_samples_per_second": 736.75, + "eval_steps_per_second": 23.024, + "step": 1297440 + }, + { + "epoch": 1.0, + "learning_rate": 2.8751253797425648e-05, + "loss": 3.5057, + "step": 1297920 + }, + { + "epoch": 1.0, + "learning_rate": 2.8742867849915128e-05, + "loss": 3.51, + "step": 1298432 + }, + { + "epoch": 1.0, + "learning_rate": 2.8734481902404608e-05, + "loss": 3.5206, + "step": 1298944 + }, + { + "epoch": 1.0, + "learning_rate": 2.8726095954894088e-05, + "loss": 3.5136, + "step": 1299456 + }, + { + "epoch": 1.0, + "learning_rate": 2.871774276499103e-05, + "loss": 3.5221, + "step": 1299968 + }, + { + "epoch": 1.0, + "learning_rate": 2.870935681748051e-05, + "loss": 3.5094, + "step": 1300480 + }, + { + "epoch": 1.0, + "learning_rate": 2.870097086996999e-05, + "loss": 3.5061, + "step": 1300992 + }, + { + "epoch": 1.0, + "learning_rate": 2.869258492245947e-05, + "loss": 3.5041, + "step": 1301504 + }, + { + "epoch": 1.0, + "learning_rate": 2.868419897494895e-05, + "loss": 3.5174, + "step": 1302016 + }, + { + "epoch": 1.0, + "learning_rate": 2.867581302743843e-05, + "loss": 3.5097, + "step": 1302528 + }, + { + "epoch": 1.0, + "learning_rate": 2.8667427079927913e-05, + "loss": 3.5212, + "step": 1303040 + }, + { + "epoch": 1.0, + "learning_rate": 2.8659041132417386e-05, + "loss": 3.5103, + "step": 1303552 + }, + { + "epoch": 1.0, + "learning_rate": 2.86506715637106e-05, + "loss": 3.5067, + "step": 1304064 + }, + { + "epoch": 1.0, + "learning_rate": 2.864228561620008e-05, + "loss": 3.5016, + "step": 1304576 + }, + { + "epoch": 1.0, + "learning_rate": 2.863389966868956e-05, + "loss": 3.5046, + "step": 1305088 + }, + { + "epoch": 1.0, + "learning_rate": 2.8625513721179038e-05, + "loss": 3.5038, + "step": 1305600 + }, + { + "epoch": 1.0, + "learning_rate": 2.8617144152472254e-05, + "loss": 3.5096, + "step": 1306112 + }, + { + "epoch": 1.0, + "learning_rate": 2.8608758204961734e-05, + "loss": 3.506, + "step": 1306624 + }, + { + "epoch": 1.0, + "learning_rate": 2.8600372257451207e-05, + "loss": 3.5019, + "step": 1307136 + }, + { + "epoch": 1.0, + "learning_rate": 2.8591986309940687e-05, + "loss": 3.5258, + "step": 1307648 + }, + { + "epoch": 1.0, + "learning_rate": 2.8583616741233903e-05, + "loss": 3.5122, + "step": 1308160 + }, + { + "epoch": 1.0, + "learning_rate": 2.8575230793723383e-05, + "loss": 3.5139, + "step": 1308672 + }, + { + "epoch": 1.0, + "learning_rate": 2.856684484621286e-05, + "loss": 3.506, + "step": 1309184 + }, + { + "epoch": 1.0, + "learning_rate": 2.855845889870234e-05, + "loss": 3.5185, + "step": 1309696 + }, + { + "epoch": 1.0, + "learning_rate": 2.8550089329995555e-05, + "loss": 3.5043, + "step": 1310208 + }, + { + "epoch": 1.0, + "learning_rate": 2.8541703382485035e-05, + "loss": 3.5086, + "step": 1310720 + }, + { + "epoch": 1.0, + "learning_rate": 2.8533317434974512e-05, + "loss": 3.5075, + "step": 1311232 + }, + { + "epoch": 1.0, + "learning_rate": 2.8524931487463992e-05, + "loss": 3.5009, + "step": 1311744 + }, + { + "epoch": 1.0, + "learning_rate": 2.8516561918757208e-05, + "loss": 3.4968, + "step": 1312256 + }, + { + "epoch": 1.01, + "learning_rate": 2.850817597124668e-05, + "loss": 3.5002, + "step": 1312768 + }, + { + "epoch": 1.01, + "learning_rate": 2.849979002373616e-05, + "loss": 3.5117, + "step": 1313280 + }, + { + "epoch": 1.01, + "learning_rate": 2.849140407622564e-05, + "loss": 3.5117, + "step": 1313792 + }, + { + "epoch": 1.01, + "learning_rate": 2.8483034507518857e-05, + "loss": 3.5111, + "step": 1314304 + }, + { + "epoch": 1.01, + "learning_rate": 2.8474648560008333e-05, + "loss": 3.5152, + "step": 1314816 + }, + { + "epoch": 1.01, + "learning_rate": 2.8466262612497813e-05, + "loss": 3.5116, + "step": 1315328 + }, + { + "epoch": 1.01, + "learning_rate": 2.8457876664987293e-05, + "loss": 3.5135, + "step": 1315840 + }, + { + "epoch": 1.01, + "learning_rate": 2.844950709628051e-05, + "loss": 3.5035, + "step": 1316352 + }, + { + "epoch": 1.01, + "learning_rate": 2.8441121148769982e-05, + "loss": 3.5082, + "step": 1316864 + }, + { + "epoch": 1.01, + "learning_rate": 2.8432735201259465e-05, + "loss": 3.4935, + "step": 1317376 + }, + { + "epoch": 1.01, + "learning_rate": 2.8424349253748945e-05, + "loss": 3.51, + "step": 1317888 + }, + { + "epoch": 1.01, + "learning_rate": 2.8415979685042155e-05, + "loss": 3.4989, + "step": 1318400 + }, + { + "epoch": 1.01, + "learning_rate": 2.8407593737531634e-05, + "loss": 3.5127, + "step": 1318912 + }, + { + "epoch": 1.01, + "learning_rate": 2.8399207790021114e-05, + "loss": 3.5016, + "step": 1319424 + }, + { + "epoch": 1.01, + "learning_rate": 2.8390821842510594e-05, + "loss": 3.5056, + "step": 1319936 + }, + { + "epoch": 1.01, + "learning_rate": 2.8382452273803807e-05, + "loss": 3.5092, + "step": 1320448 + }, + { + "epoch": 1.01, + "learning_rate": 2.8374066326293287e-05, + "loss": 3.5023, + "step": 1320960 + }, + { + "epoch": 1.01, + "learning_rate": 2.8365680378782767e-05, + "loss": 3.4997, + "step": 1321472 + }, + { + "epoch": 1.01, + "learning_rate": 2.8357310810075983e-05, + "loss": 3.4886, + "step": 1321984 + }, + { + "epoch": 1.01, + "learning_rate": 2.8348924862565456e-05, + "loss": 3.5011, + "step": 1322496 + }, + { + "epoch": 1.01, + "learning_rate": 2.8340538915054936e-05, + "loss": 3.5123, + "step": 1323008 + }, + { + "epoch": 1.01, + "learning_rate": 2.833215296754442e-05, + "loss": 3.5067, + "step": 1323520 + }, + { + "epoch": 1.01, + "learning_rate": 2.83237670200339e-05, + "loss": 3.5027, + "step": 1324032 + }, + { + "epoch": 1.01, + "learning_rate": 2.831538107252338e-05, + "loss": 3.4941, + "step": 1324544 + }, + { + "epoch": 1.01, + "learning_rate": 2.830699512501286e-05, + "loss": 3.4978, + "step": 1325056 + }, + { + "epoch": 1.01, + "learning_rate": 2.829860917750234e-05, + "loss": 3.4895, + "step": 1325568 + }, + { + "epoch": 1.01, + "learning_rate": 2.8290239608795548e-05, + "loss": 3.5169, + "step": 1326080 + }, + { + "epoch": 1.01, + "learning_rate": 2.8281853661285028e-05, + "loss": 3.4933, + "step": 1326592 + }, + { + "epoch": 1.01, + "learning_rate": 2.8273467713774508e-05, + "loss": 3.5115, + "step": 1327104 + }, + { + "epoch": 1.01, + "learning_rate": 2.826508176626399e-05, + "loss": 3.5013, + "step": 1327616 + }, + { + "epoch": 1.01, + "learning_rate": 2.825669581875347e-05, + "loss": 3.4927, + "step": 1328128 + }, + { + "epoch": 1.01, + "learning_rate": 2.824830987124295e-05, + "loss": 3.5034, + "step": 1328640 + }, + { + "epoch": 1.01, + "learning_rate": 2.823992392373243e-05, + "loss": 3.5013, + "step": 1329152 + }, + { + "epoch": 1.01, + "learning_rate": 2.823153797622191e-05, + "loss": 3.4961, + "step": 1329664 + }, + { + "epoch": 1.01, + "learning_rate": 2.822316840751512e-05, + "loss": 3.4962, + "step": 1330176 + }, + { + "epoch": 1.01, + "learning_rate": 2.82147824600046e-05, + "loss": 3.5116, + "step": 1330688 + }, + { + "epoch": 1.01, + "learning_rate": 2.8206396512494084e-05, + "loss": 3.5007, + "step": 1331200 + }, + { + "epoch": 1.01, + "learning_rate": 2.8198010564983563e-05, + "loss": 3.4944, + "step": 1331712 + }, + { + "epoch": 1.01, + "learning_rate": 2.8189640996276773e-05, + "loss": 3.4944, + "step": 1332224 + }, + { + "epoch": 1.01, + "learning_rate": 2.8181255048766253e-05, + "loss": 3.4944, + "step": 1332736 + }, + { + "epoch": 1.01, + "learning_rate": 2.8172869101255732e-05, + "loss": 3.4991, + "step": 1333248 + }, + { + "epoch": 1.01, + "learning_rate": 2.8164483153745212e-05, + "loss": 3.5156, + "step": 1333760 + }, + { + "epoch": 1.01, + "learning_rate": 2.8156113585038425e-05, + "loss": 3.4999, + "step": 1334272 + }, + { + "epoch": 1.01, + "learning_rate": 2.8147727637527905e-05, + "loss": 3.5119, + "step": 1334784 + }, + { + "epoch": 1.01, + "learning_rate": 2.8139341690017385e-05, + "loss": 3.5118, + "step": 1335296 + }, + { + "epoch": 1.01, + "learning_rate": 2.8130955742506865e-05, + "loss": 3.5053, + "step": 1335808 + }, + { + "epoch": 1.01, + "learning_rate": 2.8122586173800074e-05, + "loss": 3.4998, + "step": 1336320 + }, + { + "epoch": 1.01, + "learning_rate": 2.8114200226289554e-05, + "loss": 3.5094, + "step": 1336832 + }, + { + "epoch": 1.01, + "learning_rate": 2.8105814278779037e-05, + "loss": 3.5086, + "step": 1337344 + }, + { + "epoch": 1.01, + "learning_rate": 2.8097444710072246e-05, + "loss": 3.5012, + "step": 1337856 + }, + { + "epoch": 1.01, + "learning_rate": 2.8089058762561726e-05, + "loss": 3.5003, + "step": 1338368 + }, + { + "epoch": 1.01, + "learning_rate": 2.8080672815051206e-05, + "loss": 3.5109, + "step": 1338880 + }, + { + "epoch": 1.01, + "learning_rate": 2.8072286867540686e-05, + "loss": 3.5124, + "step": 1339392 + }, + { + "epoch": 1.01, + "learning_rate": 2.8063900920030166e-05, + "loss": 3.5002, + "step": 1339904 + }, + { + "epoch": 1.01, + "learning_rate": 2.8055514972519643e-05, + "loss": 3.4901, + "step": 1340416 + }, + { + "epoch": 1.01, + "learning_rate": 2.8047129025009123e-05, + "loss": 3.4934, + "step": 1340928 + }, + { + "epoch": 1.01, + "learning_rate": 2.8038743077498603e-05, + "loss": 3.508, + "step": 1341440 + }, + { + "epoch": 1.01, + "learning_rate": 2.803037350879181e-05, + "loss": 3.5064, + "step": 1341952 + }, + { + "epoch": 1.01, + "learning_rate": 2.802198756128129e-05, + "loss": 3.5089, + "step": 1342464 + }, + { + "epoch": 1.01, + "learning_rate": 2.8013601613770775e-05, + "loss": 3.4987, + "step": 1342976 + }, + { + "epoch": 1.02, + "learning_rate": 2.8005215666260255e-05, + "loss": 3.4984, + "step": 1343488 + }, + { + "epoch": 1.02, + "learning_rate": 2.7996846097553464e-05, + "loss": 3.4961, + "step": 1344000 + }, + { + "epoch": 1.02, + "learning_rate": 2.7988460150042944e-05, + "loss": 3.4988, + "step": 1344512 + }, + { + "epoch": 1.02, + "learning_rate": 2.7980074202532424e-05, + "loss": 3.5017, + "step": 1345024 + }, + { + "epoch": 1.02, + "learning_rate": 2.797170463382564e-05, + "loss": 3.5068, + "step": 1345536 + }, + { + "epoch": 1.02, + "learning_rate": 2.7963318686315116e-05, + "loss": 3.5182, + "step": 1346048 + }, + { + "epoch": 1.02, + "learning_rate": 2.7954932738804596e-05, + "loss": 3.5068, + "step": 1346560 + }, + { + "epoch": 1.02, + "learning_rate": 2.7946546791294076e-05, + "loss": 3.494, + "step": 1347072 + }, + { + "epoch": 1.02, + "learning_rate": 2.7938160843783556e-05, + "loss": 3.5078, + "step": 1347584 + }, + { + "epoch": 1.02, + "learning_rate": 2.7929774896273036e-05, + "loss": 3.5042, + "step": 1348096 + }, + { + "epoch": 1.02, + "learning_rate": 2.7921388948762516e-05, + "loss": 3.5055, + "step": 1348608 + }, + { + "epoch": 1.02, + "learning_rate": 2.7913003001251996e-05, + "loss": 3.5053, + "step": 1349120 + }, + { + "epoch": 1.02, + "learning_rate": 2.790463343254521e-05, + "loss": 3.502, + "step": 1349632 + }, + { + "epoch": 1.02, + "learning_rate": 2.789624748503469e-05, + "loss": 3.5016, + "step": 1350144 + }, + { + "epoch": 1.02, + "learning_rate": 2.788786153752417e-05, + "loss": 3.5106, + "step": 1350656 + }, + { + "epoch": 1.02, + "learning_rate": 2.787947559001365e-05, + "loss": 3.4873, + "step": 1351168 + }, + { + "epoch": 1.02, + "learning_rate": 2.7871106021306858e-05, + "loss": 3.498, + "step": 1351680 + }, + { + "epoch": 1.02, + "learning_rate": 2.7862720073796338e-05, + "loss": 3.5004, + "step": 1352192 + }, + { + "epoch": 1.02, + "learning_rate": 2.785433412628582e-05, + "loss": 3.504, + "step": 1352704 + }, + { + "epoch": 1.02, + "learning_rate": 2.78459481787753e-05, + "loss": 3.4903, + "step": 1353216 + }, + { + "epoch": 1.02, + "learning_rate": 2.783757861006851e-05, + "loss": 3.5048, + "step": 1353728 + }, + { + "epoch": 1.02, + "learning_rate": 2.782919266255799e-05, + "loss": 3.4935, + "step": 1354240 + }, + { + "epoch": 1.02, + "learning_rate": 2.782080671504747e-05, + "loss": 3.4995, + "step": 1354752 + }, + { + "epoch": 1.02, + "learning_rate": 2.781242076753695e-05, + "loss": 3.5007, + "step": 1355264 + }, + { + "epoch": 1.02, + "learning_rate": 2.7804051198830162e-05, + "loss": 3.5017, + "step": 1355776 + }, + { + "epoch": 1.02, + "learning_rate": 2.7795665251319642e-05, + "loss": 3.5153, + "step": 1356288 + }, + { + "epoch": 1.02, + "learning_rate": 2.7787279303809122e-05, + "loss": 3.5108, + "step": 1356800 + }, + { + "epoch": 1.02, + "learning_rate": 2.7778893356298602e-05, + "loss": 3.5011, + "step": 1357312 + }, + { + "epoch": 1.02, + "learning_rate": 2.777052378759181e-05, + "loss": 3.501, + "step": 1357824 + }, + { + "epoch": 1.02, + "learning_rate": 2.776213784008129e-05, + "loss": 3.5043, + "step": 1358336 + }, + { + "epoch": 1.02, + "learning_rate": 2.7753751892570775e-05, + "loss": 3.4984, + "step": 1358848 + }, + { + "epoch": 1.02, + "learning_rate": 2.7745365945060254e-05, + "loss": 3.4962, + "step": 1359360 + }, + { + "epoch": 1.02, + "learning_rate": 2.7736996376353464e-05, + "loss": 3.4979, + "step": 1359872 + }, + { + "epoch": 1.02, + "learning_rate": 2.7728610428842944e-05, + "loss": 3.4994, + "step": 1360384 + }, + { + "epoch": 1.02, + "learning_rate": 2.7720224481332424e-05, + "loss": 3.5009, + "step": 1360896 + }, + { + "epoch": 1.02, + "learning_rate": 2.7711838533821903e-05, + "loss": 3.4914, + "step": 1361408 + }, + { + "epoch": 1.02, + "learning_rate": 2.7703468965115116e-05, + "loss": 3.5022, + "step": 1361920 + }, + { + "epoch": 1.02, + "learning_rate": 2.7695083017604596e-05, + "loss": 3.4955, + "step": 1362432 + }, + { + "epoch": 1.02, + "learning_rate": 2.7686697070094076e-05, + "loss": 3.4969, + "step": 1362944 + }, + { + "epoch": 1.02, + "learning_rate": 2.7678311122583556e-05, + "loss": 3.4925, + "step": 1363456 + }, + { + "epoch": 1.02, + "learning_rate": 2.7669941553876765e-05, + "loss": 3.5108, + "step": 1363968 + }, + { + "epoch": 1.02, + "learning_rate": 2.7661555606366245e-05, + "loss": 3.5178, + "step": 1364480 + }, + { + "epoch": 1.02, + "learning_rate": 2.7653169658855728e-05, + "loss": 3.5023, + "step": 1364992 + }, + { + "epoch": 1.02, + "learning_rate": 2.7644783711345208e-05, + "loss": 3.4926, + "step": 1365504 + }, + { + "epoch": 1.02, + "learning_rate": 2.7636414142638417e-05, + "loss": 3.5014, + "step": 1366016 + }, + { + "epoch": 1.02, + "learning_rate": 2.7628028195127897e-05, + "loss": 3.5045, + "step": 1366528 + }, + { + "epoch": 1.02, + "learning_rate": 2.7619642247617377e-05, + "loss": 3.5069, + "step": 1367040 + }, + { + "epoch": 1.02, + "learning_rate": 2.7611256300106857e-05, + "loss": 3.5033, + "step": 1367552 + }, + { + "epoch": 1.02, + "learning_rate": 2.760288673140007e-05, + "loss": 3.5081, + "step": 1368064 + }, + { + "epoch": 1.02, + "learning_rate": 2.759450078388955e-05, + "loss": 3.4968, + "step": 1368576 + }, + { + "epoch": 1.02, + "learning_rate": 2.758611483637903e-05, + "loss": 3.5059, + "step": 1369088 + }, + { + "epoch": 1.02, + "learning_rate": 2.757774526767224e-05, + "loss": 3.4961, + "step": 1369600 + }, + { + "epoch": 1.02, + "learning_rate": 2.756937569896545e-05, + "loss": 3.506, + "step": 1370112 + }, + { + "epoch": 1.02, + "learning_rate": 2.756098975145493e-05, + "loss": 3.4994, + "step": 1370624 + }, + { + "epoch": 1.02, + "learning_rate": 2.755260380394441e-05, + "loss": 3.4931, + "step": 1371136 + }, + { + "epoch": 1.02, + "learning_rate": 2.754421785643389e-05, + "loss": 3.5106, + "step": 1371648 + }, + { + "epoch": 1.02, + "learning_rate": 2.753583190892337e-05, + "loss": 3.4996, + "step": 1372160 + }, + { + "epoch": 1.02, + "learning_rate": 2.752744596141285e-05, + "loss": 3.5094, + "step": 1372672 + }, + { + "epoch": 1.02, + "learning_rate": 2.751906001390233e-05, + "loss": 3.491, + "step": 1373184 + }, + { + "epoch": 1.02, + "learning_rate": 2.751069044519554e-05, + "loss": 3.4931, + "step": 1373696 + }, + { + "epoch": 1.03, + "eval_loss": 3.8459558486938477, + "eval_runtime": 491.8598, + "eval_samples_per_second": 775.813, + "eval_steps_per_second": 24.245, + "step": 1373760 + }, + { + "epoch": 0.0, + "learning_rate": 2.7502304497685023e-05, + "loss": 3.4945, + "step": 1374208 + }, + { + "epoch": 0.0, + "learning_rate": 2.7493918550174503e-05, + "loss": 3.4918, + "step": 1374720 + }, + { + "epoch": 0.0, + "learning_rate": 2.7485532602663983e-05, + "loss": 3.5104, + "step": 1375232 + }, + { + "epoch": 0.0, + "learning_rate": 2.7477146655153463e-05, + "loss": 3.4994, + "step": 1375744 + }, + { + "epoch": 0.0, + "learning_rate": 2.7468793465250405e-05, + "loss": 3.514, + "step": 1376256 + }, + { + "epoch": 0.0, + "learning_rate": 2.7460407517739885e-05, + "loss": 3.494, + "step": 1376768 + }, + { + "epoch": 0.0, + "learning_rate": 2.7452021570229365e-05, + "loss": 3.4949, + "step": 1377280 + }, + { + "epoch": 0.0, + "learning_rate": 2.7443635622718845e-05, + "loss": 3.4862, + "step": 1377792 + }, + { + "epoch": 0.0, + "learning_rate": 2.7435249675208325e-05, + "loss": 3.5009, + "step": 1378304 + }, + { + "epoch": 0.0, + "learning_rate": 2.7426863727697805e-05, + "loss": 3.5023, + "step": 1378816 + }, + { + "epoch": 0.0, + "learning_rate": 2.7418477780187285e-05, + "loss": 3.5033, + "step": 1379328 + }, + { + "epoch": 0.0, + "learning_rate": 2.7410091832676764e-05, + "loss": 3.4997, + "step": 1379840 + }, + { + "epoch": 0.0, + "learning_rate": 2.7401722263969977e-05, + "loss": 3.4922, + "step": 1380352 + }, + { + "epoch": 0.0, + "learning_rate": 2.7393352695263186e-05, + "loss": 3.4903, + "step": 1380864 + }, + { + "epoch": 0.0, + "learning_rate": 2.7384966747752666e-05, + "loss": 3.4887, + "step": 1381376 + }, + { + "epoch": 0.0, + "learning_rate": 2.7376580800242146e-05, + "loss": 3.4925, + "step": 1381888 + }, + { + "epoch": 0.0, + "learning_rate": 2.7368194852731626e-05, + "loss": 3.4925, + "step": 1382400 + }, + { + "epoch": 0.0, + "learning_rate": 2.7359808905221106e-05, + "loss": 3.4911, + "step": 1382912 + }, + { + "epoch": 0.0, + "learning_rate": 2.7351422957710586e-05, + "loss": 3.4891, + "step": 1383424 + }, + { + "epoch": 0.0, + "learning_rate": 2.734303701020007e-05, + "loss": 3.5143, + "step": 1383936 + }, + { + "epoch": 0.0, + "learning_rate": 2.7334651062689542e-05, + "loss": 3.4994, + "step": 1384448 + }, + { + "epoch": 0.0, + "learning_rate": 2.7326281493982758e-05, + "loss": 3.5012, + "step": 1384960 + }, + { + "epoch": 0.0, + "learning_rate": 2.7317895546472238e-05, + "loss": 3.493, + "step": 1385472 + }, + { + "epoch": 0.0, + "learning_rate": 2.7309509598961718e-05, + "loss": 3.5075, + "step": 1385984 + }, + { + "epoch": 0.0, + "learning_rate": 2.7301123651451195e-05, + "loss": 3.4851, + "step": 1386496 + }, + { + "epoch": 0.0, + "learning_rate": 2.729275408274441e-05, + "loss": 3.4971, + "step": 1387008 + }, + { + "epoch": 0.0, + "learning_rate": 2.728436813523389e-05, + "loss": 3.4966, + "step": 1387520 + }, + { + "epoch": 0.0, + "learning_rate": 2.72759985665271e-05, + "loss": 3.4921, + "step": 1388032 + }, + { + "epoch": 0.0, + "learning_rate": 2.726761261901658e-05, + "loss": 3.4835, + "step": 1388544 + }, + { + "epoch": 0.01, + "learning_rate": 2.725922667150606e-05, + "loss": 3.4851, + "step": 1389056 + }, + { + "epoch": 0.01, + "learning_rate": 2.725084072399554e-05, + "loss": 3.4969, + "step": 1389568 + }, + { + "epoch": 0.01, + "learning_rate": 2.7242454776485016e-05, + "loss": 3.4987, + "step": 1390080 + }, + { + "epoch": 0.01, + "learning_rate": 2.7234068828974496e-05, + "loss": 3.4996, + "step": 1390592 + }, + { + "epoch": 0.01, + "learning_rate": 2.7225682881463976e-05, + "loss": 3.4999, + "step": 1391104 + }, + { + "epoch": 0.01, + "learning_rate": 2.7217296933953456e-05, + "loss": 3.4939, + "step": 1391616 + }, + { + "epoch": 0.01, + "learning_rate": 2.720892736524667e-05, + "loss": 3.5015, + "step": 1392128 + }, + { + "epoch": 0.01, + "learning_rate": 2.7200557796539884e-05, + "loss": 3.4916, + "step": 1392640 + }, + { + "epoch": 0.01, + "learning_rate": 2.7192171849029364e-05, + "loss": 3.4944, + "step": 1393152 + }, + { + "epoch": 0.01, + "learning_rate": 2.7183785901518837e-05, + "loss": 3.4809, + "step": 1393664 + }, + { + "epoch": 0.01, + "learning_rate": 2.7175399954008317e-05, + "loss": 3.4988, + "step": 1394176 + }, + { + "epoch": 0.01, + "learning_rate": 2.7167014006497797e-05, + "loss": 3.4898, + "step": 1394688 + }, + { + "epoch": 0.01, + "learning_rate": 2.7158628058987277e-05, + "loss": 3.4998, + "step": 1395200 + }, + { + "epoch": 0.01, + "learning_rate": 2.715024211147676e-05, + "loss": 3.4904, + "step": 1395712 + }, + { + "epoch": 0.01, + "learning_rate": 2.714185616396624e-05, + "loss": 3.4882, + "step": 1396224 + }, + { + "epoch": 0.01, + "learning_rate": 2.713348659525945e-05, + "loss": 3.5024, + "step": 1396736 + }, + { + "epoch": 0.01, + "learning_rate": 2.712510064774893e-05, + "loss": 3.4881, + "step": 1397248 + }, + { + "epoch": 0.01, + "learning_rate": 2.711671470023841e-05, + "loss": 3.4891, + "step": 1397760 + }, + { + "epoch": 0.01, + "learning_rate": 2.7108345131531622e-05, + "loss": 3.4727, + "step": 1398272 + }, + { + "epoch": 0.01, + "learning_rate": 2.7099975562824838e-05, + "loss": 3.4909, + "step": 1398784 + }, + { + "epoch": 0.01, + "learning_rate": 2.709158961531431e-05, + "loss": 3.496, + "step": 1399296 + }, + { + "epoch": 0.01, + "learning_rate": 2.708320366780379e-05, + "loss": 3.4927, + "step": 1399808 + }, + { + "epoch": 0.01, + "learning_rate": 2.707481772029327e-05, + "loss": 3.4926, + "step": 1400320 + }, + { + "epoch": 0.01, + "learning_rate": 2.706643177278275e-05, + "loss": 3.478, + "step": 1400832 + }, + { + "epoch": 0.01, + "learning_rate": 2.705804582527223e-05, + "loss": 3.4877, + "step": 1401344 + }, + { + "epoch": 0.01, + "learning_rate": 2.7049659877761714e-05, + "loss": 3.4772, + "step": 1401856 + }, + { + "epoch": 0.01, + "learning_rate": 2.7041290309054923e-05, + "loss": 3.5024, + "step": 1402368 + }, + { + "epoch": 0.01, + "learning_rate": 2.7032904361544403e-05, + "loss": 3.4807, + "step": 1402880 + }, + { + "epoch": 0.01, + "learning_rate": 2.7024518414033883e-05, + "loss": 3.4989, + "step": 1403392 + }, + { + "epoch": 0.01, + "learning_rate": 2.7016132466523363e-05, + "loss": 3.4933, + "step": 1403904 + }, + { + "epoch": 0.01, + "learning_rate": 2.7007746519012843e-05, + "loss": 3.4794, + "step": 1404416 + }, + { + "epoch": 0.01, + "learning_rate": 2.6999360571502323e-05, + "loss": 3.4869, + "step": 1404928 + }, + { + "epoch": 0.01, + "learning_rate": 2.6990974623991807e-05, + "loss": 3.4915, + "step": 1405440 + }, + { + "epoch": 0.01, + "learning_rate": 2.6982588676481286e-05, + "loss": 3.4802, + "step": 1405952 + }, + { + "epoch": 0.01, + "learning_rate": 2.6974219107774496e-05, + "loss": 3.4853, + "step": 1406464 + }, + { + "epoch": 0.01, + "learning_rate": 2.6965833160263976e-05, + "loss": 3.4955, + "step": 1406976 + }, + { + "epoch": 0.01, + "learning_rate": 2.6957447212753455e-05, + "loss": 3.4931, + "step": 1407488 + }, + { + "epoch": 0.01, + "learning_rate": 2.6949061265242935e-05, + "loss": 3.4789, + "step": 1408000 + }, + { + "epoch": 0.01, + "learning_rate": 2.6940691696536148e-05, + "loss": 3.4856, + "step": 1408512 + }, + { + "epoch": 0.01, + "learning_rate": 2.6932305749025628e-05, + "loss": 3.4803, + "step": 1409024 + }, + { + "epoch": 0.01, + "learning_rate": 2.6923919801515108e-05, + "loss": 3.4842, + "step": 1409536 + }, + { + "epoch": 0.01, + "learning_rate": 2.6915533854004588e-05, + "loss": 3.4995, + "step": 1410048 + }, + { + "epoch": 0.01, + "learning_rate": 2.6907164285297797e-05, + "loss": 3.4868, + "step": 1410560 + }, + { + "epoch": 0.01, + "learning_rate": 2.689879471659101e-05, + "loss": 3.5005, + "step": 1411072 + }, + { + "epoch": 0.01, + "learning_rate": 2.689040876908049e-05, + "loss": 3.4961, + "step": 1411584 + }, + { + "epoch": 0.01, + "learning_rate": 2.688202282156997e-05, + "loss": 3.4957, + "step": 1412096 + }, + { + "epoch": 0.01, + "learning_rate": 2.687363687405945e-05, + "loss": 3.4851, + "step": 1412608 + }, + { + "epoch": 0.01, + "learning_rate": 2.686525092654893e-05, + "loss": 3.4987, + "step": 1413120 + }, + { + "epoch": 0.01, + "learning_rate": 2.685686497903841e-05, + "loss": 3.4945, + "step": 1413632 + }, + { + "epoch": 0.01, + "learning_rate": 2.684849541033162e-05, + "loss": 3.4923, + "step": 1414144 + }, + { + "epoch": 0.01, + "learning_rate": 2.68401094628211e-05, + "loss": 3.4872, + "step": 1414656 + }, + { + "epoch": 0.01, + "learning_rate": 2.683172351531058e-05, + "loss": 3.4945, + "step": 1415168 + }, + { + "epoch": 0.01, + "learning_rate": 2.682333756780006e-05, + "loss": 3.5032, + "step": 1415680 + }, + { + "epoch": 0.01, + "learning_rate": 2.681495162028954e-05, + "loss": 3.4894, + "step": 1416192 + }, + { + "epoch": 0.01, + "learning_rate": 2.680656567277902e-05, + "loss": 3.475, + "step": 1416704 + }, + { + "epoch": 0.01, + "learning_rate": 2.679819610407223e-05, + "loss": 3.4794, + "step": 1417216 + }, + { + "epoch": 0.01, + "learning_rate": 2.678981015656171e-05, + "loss": 3.4964, + "step": 1417728 + }, + { + "epoch": 0.01, + "learning_rate": 2.6781424209051194e-05, + "loss": 3.4943, + "step": 1418240 + }, + { + "epoch": 0.01, + "learning_rate": 2.6773038261540674e-05, + "loss": 3.4977, + "step": 1418752 + }, + { + "epoch": 0.01, + "learning_rate": 2.6764652314030147e-05, + "loss": 3.4847, + "step": 1419264 + }, + { + "epoch": 0.02, + "learning_rate": 2.6756266366519627e-05, + "loss": 3.488, + "step": 1419776 + }, + { + "epoch": 0.02, + "learning_rate": 2.6747880419009107e-05, + "loss": 3.4805, + "step": 1420288 + }, + { + "epoch": 0.02, + "learning_rate": 2.6739494471498587e-05, + "loss": 3.4873, + "step": 1420800 + }, + { + "epoch": 0.02, + "learning_rate": 2.67311249027918e-05, + "loss": 3.4892, + "step": 1421312 + }, + { + "epoch": 0.02, + "learning_rate": 2.6722755334085015e-05, + "loss": 3.4958, + "step": 1421824 + }, + { + "epoch": 0.02, + "learning_rate": 2.6714369386574495e-05, + "loss": 3.5079, + "step": 1422336 + }, + { + "epoch": 0.02, + "learning_rate": 2.6705983439063968e-05, + "loss": 3.4911, + "step": 1422848 + }, + { + "epoch": 0.02, + "learning_rate": 2.6697597491553448e-05, + "loss": 3.4855, + "step": 1423360 + }, + { + "epoch": 0.02, + "learning_rate": 2.668921154404293e-05, + "loss": 3.4933, + "step": 1423872 + }, + { + "epoch": 0.02, + "learning_rate": 2.668082559653241e-05, + "loss": 3.4884, + "step": 1424384 + }, + { + "epoch": 0.02, + "learning_rate": 2.667243964902189e-05, + "loss": 3.4978, + "step": 1424896 + }, + { + "epoch": 0.02, + "learning_rate": 2.666405370151137e-05, + "loss": 3.4918, + "step": 1425408 + }, + { + "epoch": 0.02, + "learning_rate": 2.665568413280458e-05, + "loss": 3.489, + "step": 1425920 + }, + { + "epoch": 0.02, + "learning_rate": 2.664729818529406e-05, + "loss": 3.4873, + "step": 1426432 + }, + { + "epoch": 0.02, + "learning_rate": 2.663891223778354e-05, + "loss": 3.4974, + "step": 1426944 + }, + { + "epoch": 0.02, + "learning_rate": 2.6630526290273024e-05, + "loss": 3.474, + "step": 1427456 + }, + { + "epoch": 0.02, + "learning_rate": 2.6622156721566233e-05, + "loss": 3.4878, + "step": 1427968 + }, + { + "epoch": 0.02, + "learning_rate": 2.6613770774055713e-05, + "loss": 3.4836, + "step": 1428480 + }, + { + "epoch": 0.02, + "learning_rate": 2.6605384826545193e-05, + "loss": 3.4914, + "step": 1428992 + }, + { + "epoch": 0.02, + "learning_rate": 2.6596998879034673e-05, + "loss": 3.4798, + "step": 1429504 + }, + { + "epoch": 0.02, + "learning_rate": 2.6588629310327885e-05, + "loss": 3.4915, + "step": 1430016 + }, + { + "epoch": 0.02, + "learning_rate": 2.6580243362817365e-05, + "loss": 3.4792, + "step": 1430528 + }, + { + "epoch": 0.02, + "learning_rate": 2.6571873794110574e-05, + "loss": 3.4864, + "step": 1431040 + }, + { + "epoch": 0.02, + "learning_rate": 2.6563487846600054e-05, + "loss": 3.4914, + "step": 1431552 + }, + { + "epoch": 0.02, + "learning_rate": 2.6555101899089534e-05, + "loss": 3.486, + "step": 1432064 + }, + { + "epoch": 0.02, + "learning_rate": 2.6546715951579014e-05, + "loss": 3.5047, + "step": 1432576 + }, + { + "epoch": 0.02, + "learning_rate": 2.6538330004068494e-05, + "loss": 3.499, + "step": 1433088 + }, + { + "epoch": 0.02, + "learning_rate": 2.6529944056557977e-05, + "loss": 3.4908, + "step": 1433600 + }, + { + "epoch": 0.02, + "learning_rate": 2.6521558109047457e-05, + "loss": 3.4847, + "step": 1434112 + }, + { + "epoch": 0.02, + "learning_rate": 2.6513172161536937e-05, + "loss": 3.489, + "step": 1434624 + }, + { + "epoch": 0.02, + "learning_rate": 2.6504802592830146e-05, + "loss": 3.4881, + "step": 1435136 + }, + { + "epoch": 0.02, + "learning_rate": 2.6496416645319626e-05, + "loss": 3.4866, + "step": 1435648 + }, + { + "epoch": 0.02, + "learning_rate": 2.6488030697809106e-05, + "loss": 3.4872, + "step": 1436160 + }, + { + "epoch": 0.02, + "learning_rate": 2.6479644750298586e-05, + "loss": 3.4821, + "step": 1436672 + }, + { + "epoch": 0.02, + "learning_rate": 2.64712751815918e-05, + "loss": 3.4897, + "step": 1437184 + }, + { + "epoch": 0.02, + "learning_rate": 2.646288923408128e-05, + "loss": 3.479, + "step": 1437696 + }, + { + "epoch": 0.02, + "learning_rate": 2.645450328657076e-05, + "loss": 3.4878, + "step": 1438208 + }, + { + "epoch": 0.02, + "learning_rate": 2.644611733906024e-05, + "loss": 3.4829, + "step": 1438720 + }, + { + "epoch": 0.02, + "learning_rate": 2.6437747770353448e-05, + "loss": 3.4836, + "step": 1439232 + }, + { + "epoch": 0.02, + "learning_rate": 2.642936182284293e-05, + "loss": 3.4798, + "step": 1439744 + }, + { + "epoch": 0.02, + "learning_rate": 2.642097587533241e-05, + "loss": 3.5011, + "step": 1440256 + }, + { + "epoch": 0.02, + "learning_rate": 2.641258992782189e-05, + "loss": 3.5023, + "step": 1440768 + }, + { + "epoch": 0.02, + "learning_rate": 2.64042203591151e-05, + "loss": 3.4935, + "step": 1441280 + }, + { + "epoch": 0.02, + "learning_rate": 2.639583441160458e-05, + "loss": 3.4774, + "step": 1441792 + }, + { + "epoch": 0.02, + "learning_rate": 2.638744846409406e-05, + "loss": 3.4916, + "step": 1442304 + }, + { + "epoch": 0.02, + "learning_rate": 2.637906251658354e-05, + "loss": 3.4883, + "step": 1442816 + }, + { + "epoch": 0.02, + "learning_rate": 2.6370692947876753e-05, + "loss": 3.4939, + "step": 1443328 + }, + { + "epoch": 0.02, + "learning_rate": 2.6362307000366232e-05, + "loss": 3.4885, + "step": 1443840 + }, + { + "epoch": 0.02, + "learning_rate": 2.6353921052855712e-05, + "loss": 3.4926, + "step": 1444352 + }, + { + "epoch": 0.02, + "learning_rate": 2.6345535105345192e-05, + "loss": 3.4873, + "step": 1444864 + }, + { + "epoch": 0.02, + "learning_rate": 2.63371655366384e-05, + "loss": 3.4943, + "step": 1445376 + }, + { + "epoch": 0.02, + "learning_rate": 2.6328779589127885e-05, + "loss": 3.4898, + "step": 1445888 + }, + { + "epoch": 0.02, + "learning_rate": 2.6320410020421094e-05, + "loss": 3.4911, + "step": 1446400 + }, + { + "epoch": 0.02, + "learning_rate": 2.6312024072910574e-05, + "loss": 3.4875, + "step": 1446912 + }, + { + "epoch": 0.02, + "learning_rate": 2.6303638125400054e-05, + "loss": 3.4815, + "step": 1447424 + }, + { + "epoch": 0.02, + "learning_rate": 2.6295252177889534e-05, + "loss": 3.4952, + "step": 1447936 + }, + { + "epoch": 0.02, + "learning_rate": 2.6286866230379014e-05, + "loss": 3.4909, + "step": 1448448 + }, + { + "epoch": 0.02, + "learning_rate": 2.6278480282868494e-05, + "loss": 3.4901, + "step": 1448960 + }, + { + "epoch": 0.02, + "learning_rate": 2.6270094335357977e-05, + "loss": 3.4789, + "step": 1449472 + }, + { + "epoch": 0.02, + "learning_rate": 2.6261708387847457e-05, + "loss": 3.4817, + "step": 1449984 + }, + { + "epoch": 0.03, + "eval_loss": 3.8460357189178467, + "eval_runtime": 306.8238, + "eval_samples_per_second": 1243.681, + "eval_steps_per_second": 38.866, + "step": 1450080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6253338819140666e-05, + "loss": 3.4846, + "step": 1450496 + }, + { + "epoch": 1.0, + "learning_rate": 2.6244952871630146e-05, + "loss": 3.4835, + "step": 1451008 + }, + { + "epoch": 1.0, + "learning_rate": 2.6236566924119626e-05, + "loss": 3.4921, + "step": 1451520 + }, + { + "epoch": 1.0, + "learning_rate": 2.6228180976609103e-05, + "loss": 3.4874, + "step": 1452032 + }, + { + "epoch": 1.0, + "learning_rate": 2.6219827786706048e-05, + "loss": 3.5037, + "step": 1452544 + }, + { + "epoch": 1.0, + "learning_rate": 2.6211441839195528e-05, + "loss": 3.4828, + "step": 1453056 + }, + { + "epoch": 1.0, + "learning_rate": 2.6203055891685007e-05, + "loss": 3.4826, + "step": 1453568 + }, + { + "epoch": 1.0, + "learning_rate": 2.6194669944174487e-05, + "loss": 3.473, + "step": 1454080 + }, + { + "epoch": 1.0, + "learning_rate": 2.6186283996663967e-05, + "loss": 3.4885, + "step": 1454592 + }, + { + "epoch": 1.0, + "learning_rate": 2.6177898049153447e-05, + "loss": 3.4883, + "step": 1455104 + }, + { + "epoch": 1.0, + "learning_rate": 2.6169512101642927e-05, + "loss": 3.4895, + "step": 1455616 + }, + { + "epoch": 1.0, + "learning_rate": 2.6161126154132404e-05, + "loss": 3.4859, + "step": 1456128 + }, + { + "epoch": 1.0, + "learning_rate": 2.615275658542562e-05, + "loss": 3.4812, + "step": 1456640 + }, + { + "epoch": 1.0, + "learning_rate": 2.61443706379151e-05, + "loss": 3.4793, + "step": 1457152 + }, + { + "epoch": 1.0, + "learning_rate": 2.6135984690404576e-05, + "loss": 3.4764, + "step": 1457664 + }, + { + "epoch": 1.0, + "learning_rate": 2.6127615121697792e-05, + "loss": 3.481, + "step": 1458176 + }, + { + "epoch": 1.0, + "learning_rate": 2.6119229174187272e-05, + "loss": 3.4809, + "step": 1458688 + }, + { + "epoch": 1.0, + "learning_rate": 2.6110843226676752e-05, + "loss": 3.4777, + "step": 1459200 + }, + { + "epoch": 1.0, + "learning_rate": 2.6102457279166225e-05, + "loss": 3.4769, + "step": 1459712 + }, + { + "epoch": 1.0, + "learning_rate": 2.6094071331655705e-05, + "loss": 3.5057, + "step": 1460224 + }, + { + "epoch": 1.0, + "learning_rate": 2.6085685384145185e-05, + "loss": 3.4851, + "step": 1460736 + }, + { + "epoch": 1.0, + "learning_rate": 2.6077299436634665e-05, + "loss": 3.485, + "step": 1461248 + }, + { + "epoch": 1.0, + "learning_rate": 2.606891348912415e-05, + "loss": 3.4836, + "step": 1461760 + }, + { + "epoch": 1.0, + "learning_rate": 2.6060543920417358e-05, + "loss": 3.4902, + "step": 1462272 + }, + { + "epoch": 1.0, + "learning_rate": 2.6052157972906837e-05, + "loss": 3.4757, + "step": 1462784 + }, + { + "epoch": 1.0, + "learning_rate": 2.6043772025396317e-05, + "loss": 3.4907, + "step": 1463296 + }, + { + "epoch": 1.0, + "learning_rate": 2.6035386077885797e-05, + "loss": 3.4804, + "step": 1463808 + }, + { + "epoch": 1.0, + "learning_rate": 2.6027032887982742e-05, + "loss": 3.4803, + "step": 1464320 + }, + { + "epoch": 1.0, + "learning_rate": 2.6018646940472226e-05, + "loss": 3.4662, + "step": 1464832 + }, + { + "epoch": 1.01, + "learning_rate": 2.60102609929617e-05, + "loss": 3.4759, + "step": 1465344 + }, + { + "epoch": 1.01, + "learning_rate": 2.600187504545118e-05, + "loss": 3.4837, + "step": 1465856 + }, + { + "epoch": 1.01, + "learning_rate": 2.599348909794066e-05, + "loss": 3.4865, + "step": 1466368 + }, + { + "epoch": 1.01, + "learning_rate": 2.598510315043014e-05, + "loss": 3.4924, + "step": 1466880 + }, + { + "epoch": 1.01, + "learning_rate": 2.597671720291962e-05, + "loss": 3.4896, + "step": 1467392 + }, + { + "epoch": 1.01, + "learning_rate": 2.5968331255409102e-05, + "loss": 3.4765, + "step": 1467904 + }, + { + "epoch": 1.01, + "learning_rate": 2.595996168670231e-05, + "loss": 3.4923, + "step": 1468416 + }, + { + "epoch": 1.01, + "learning_rate": 2.595159211799552e-05, + "loss": 3.4772, + "step": 1468928 + }, + { + "epoch": 1.01, + "learning_rate": 2.5943206170485e-05, + "loss": 3.4834, + "step": 1469440 + }, + { + "epoch": 1.01, + "learning_rate": 2.593482022297448e-05, + "loss": 3.4684, + "step": 1469952 + }, + { + "epoch": 1.01, + "learning_rate": 2.5926434275463964e-05, + "loss": 3.4854, + "step": 1470464 + }, + { + "epoch": 1.01, + "learning_rate": 2.5918048327953444e-05, + "loss": 3.4772, + "step": 1470976 + }, + { + "epoch": 1.01, + "learning_rate": 2.5909662380442923e-05, + "loss": 3.488, + "step": 1471488 + }, + { + "epoch": 1.01, + "learning_rate": 2.5901276432932403e-05, + "loss": 3.48, + "step": 1472000 + }, + { + "epoch": 1.01, + "learning_rate": 2.5892890485421883e-05, + "loss": 3.4743, + "step": 1472512 + }, + { + "epoch": 1.01, + "learning_rate": 2.5884520916715092e-05, + "loss": 3.4905, + "step": 1473024 + }, + { + "epoch": 1.01, + "learning_rate": 2.5876134969204572e-05, + "loss": 3.4787, + "step": 1473536 + }, + { + "epoch": 1.01, + "learning_rate": 2.5867749021694056e-05, + "loss": 3.4741, + "step": 1474048 + }, + { + "epoch": 1.01, + "learning_rate": 2.5859379452987265e-05, + "loss": 3.4625, + "step": 1474560 + }, + { + "epoch": 1.01, + "learning_rate": 2.5851009884280474e-05, + "loss": 3.4754, + "step": 1475072 + }, + { + "epoch": 1.01, + "learning_rate": 2.5842623936769954e-05, + "loss": 3.4848, + "step": 1475584 + }, + { + "epoch": 1.01, + "learning_rate": 2.5834237989259434e-05, + "loss": 3.4802, + "step": 1476096 + }, + { + "epoch": 1.01, + "learning_rate": 2.5825852041748917e-05, + "loss": 3.4802, + "step": 1476608 + }, + { + "epoch": 1.01, + "learning_rate": 2.5817466094238397e-05, + "loss": 3.4679, + "step": 1477120 + }, + { + "epoch": 1.01, + "learning_rate": 2.5809080146727877e-05, + "loss": 3.4761, + "step": 1477632 + }, + { + "epoch": 1.01, + "learning_rate": 2.5800694199217357e-05, + "loss": 3.4635, + "step": 1478144 + }, + { + "epoch": 1.01, + "learning_rate": 2.5792324630510566e-05, + "loss": 3.4878, + "step": 1478656 + }, + { + "epoch": 1.01, + "learning_rate": 2.5783938683000046e-05, + "loss": 3.4731, + "step": 1479168 + }, + { + "epoch": 1.01, + "learning_rate": 2.5775552735489526e-05, + "loss": 3.4806, + "step": 1479680 + }, + { + "epoch": 1.01, + "learning_rate": 2.576716678797901e-05, + "loss": 3.4796, + "step": 1480192 + }, + { + "epoch": 1.01, + "learning_rate": 2.575878084046849e-05, + "loss": 3.47, + "step": 1480704 + }, + { + "epoch": 1.01, + "learning_rate": 2.575039489295797e-05, + "loss": 3.4712, + "step": 1481216 + }, + { + "epoch": 1.01, + "learning_rate": 2.574200894544745e-05, + "loss": 3.4788, + "step": 1481728 + }, + { + "epoch": 1.01, + "learning_rate": 2.573362299793693e-05, + "loss": 3.4676, + "step": 1482240 + }, + { + "epoch": 1.01, + "learning_rate": 2.572525342923014e-05, + "loss": 3.4776, + "step": 1482752 + }, + { + "epoch": 1.01, + "learning_rate": 2.571686748171962e-05, + "loss": 3.4793, + "step": 1483264 + }, + { + "epoch": 1.01, + "learning_rate": 2.57084815342091e-05, + "loss": 3.4823, + "step": 1483776 + }, + { + "epoch": 1.01, + "learning_rate": 2.570009558669858e-05, + "loss": 3.4655, + "step": 1484288 + }, + { + "epoch": 1.01, + "learning_rate": 2.569172601799179e-05, + "loss": 3.4732, + "step": 1484800 + }, + { + "epoch": 1.01, + "learning_rate": 2.568334007048127e-05, + "loss": 3.466, + "step": 1485312 + }, + { + "epoch": 1.01, + "learning_rate": 2.567495412297075e-05, + "loss": 3.4717, + "step": 1485824 + }, + { + "epoch": 1.01, + "learning_rate": 2.566656817546023e-05, + "loss": 3.4847, + "step": 1486336 + }, + { + "epoch": 1.01, + "learning_rate": 2.5658198606753443e-05, + "loss": 3.4739, + "step": 1486848 + }, + { + "epoch": 1.01, + "learning_rate": 2.5649812659242923e-05, + "loss": 3.4899, + "step": 1487360 + }, + { + "epoch": 1.01, + "learning_rate": 2.5641426711732403e-05, + "loss": 3.4853, + "step": 1487872 + }, + { + "epoch": 1.01, + "learning_rate": 2.5633057143025612e-05, + "loss": 3.4863, + "step": 1488384 + }, + { + "epoch": 1.01, + "learning_rate": 2.5624671195515092e-05, + "loss": 3.4683, + "step": 1488896 + }, + { + "epoch": 1.01, + "learning_rate": 2.5616285248004572e-05, + "loss": 3.4841, + "step": 1489408 + }, + { + "epoch": 1.01, + "learning_rate": 2.5607899300494055e-05, + "loss": 3.4867, + "step": 1489920 + }, + { + "epoch": 1.01, + "learning_rate": 2.5599529731787264e-05, + "loss": 3.4758, + "step": 1490432 + }, + { + "epoch": 1.01, + "learning_rate": 2.5591143784276744e-05, + "loss": 3.4788, + "step": 1490944 + }, + { + "epoch": 1.01, + "learning_rate": 2.5582757836766224e-05, + "loss": 3.4829, + "step": 1491456 + }, + { + "epoch": 1.01, + "learning_rate": 2.5574371889255704e-05, + "loss": 3.4923, + "step": 1491968 + }, + { + "epoch": 1.01, + "learning_rate": 2.556598594174518e-05, + "loss": 3.4766, + "step": 1492480 + }, + { + "epoch": 1.01, + "learning_rate": 2.555759999423466e-05, + "loss": 3.4631, + "step": 1492992 + }, + { + "epoch": 1.01, + "learning_rate": 2.554921404672414e-05, + "loss": 3.4713, + "step": 1493504 + }, + { + "epoch": 1.01, + "learning_rate": 2.554082809921362e-05, + "loss": 3.4797, + "step": 1494016 + }, + { + "epoch": 1.01, + "learning_rate": 2.553245853050683e-05, + "loss": 3.4828, + "step": 1494528 + }, + { + "epoch": 1.01, + "learning_rate": 2.552407258299631e-05, + "loss": 3.4801, + "step": 1495040 + }, + { + "epoch": 1.01, + "learning_rate": 2.5515686635485793e-05, + "loss": 3.4749, + "step": 1495552 + }, + { + "epoch": 1.02, + "learning_rate": 2.5507300687975273e-05, + "loss": 3.4761, + "step": 1496064 + }, + { + "epoch": 1.02, + "learning_rate": 2.5498931119268482e-05, + "loss": 3.4653, + "step": 1496576 + }, + { + "epoch": 1.02, + "learning_rate": 2.5490545171757962e-05, + "loss": 3.4732, + "step": 1497088 + }, + { + "epoch": 1.02, + "learning_rate": 2.5482159224247442e-05, + "loss": 3.4738, + "step": 1497600 + }, + { + "epoch": 1.02, + "learning_rate": 2.5473789655540655e-05, + "loss": 3.4893, + "step": 1498112 + }, + { + "epoch": 1.02, + "learning_rate": 2.5465403708030135e-05, + "loss": 3.4995, + "step": 1498624 + }, + { + "epoch": 1.02, + "learning_rate": 2.5457017760519614e-05, + "loss": 3.4762, + "step": 1499136 + }, + { + "epoch": 1.02, + "learning_rate": 2.5448631813009094e-05, + "loss": 3.4706, + "step": 1499648 + }, + { + "epoch": 1.02, + "learning_rate": 2.5440245865498574e-05, + "loss": 3.4851, + "step": 1500160 + }, + { + "epoch": 1.02, + "learning_rate": 2.5431859917988054e-05, + "loss": 3.4743, + "step": 1500672 + }, + { + "epoch": 1.02, + "learning_rate": 2.5423473970477534e-05, + "loss": 3.4867, + "step": 1501184 + }, + { + "epoch": 1.02, + "learning_rate": 2.5415088022967014e-05, + "loss": 3.4761, + "step": 1501696 + }, + { + "epoch": 1.02, + "learning_rate": 2.5406718454260227e-05, + "loss": 3.4786, + "step": 1502208 + }, + { + "epoch": 1.02, + "learning_rate": 2.5398332506749707e-05, + "loss": 3.477, + "step": 1502720 + }, + { + "epoch": 1.02, + "learning_rate": 2.5389946559239187e-05, + "loss": 3.4872, + "step": 1503232 + }, + { + "epoch": 1.02, + "learning_rate": 2.5381560611728667e-05, + "loss": 3.4622, + "step": 1503744 + }, + { + "epoch": 1.02, + "learning_rate": 2.5373191043021876e-05, + "loss": 3.4739, + "step": 1504256 + }, + { + "epoch": 1.02, + "learning_rate": 2.5364805095511356e-05, + "loss": 3.4698, + "step": 1504768 + }, + { + "epoch": 1.02, + "learning_rate": 2.5356419148000836e-05, + "loss": 3.4832, + "step": 1505280 + }, + { + "epoch": 1.02, + "learning_rate": 2.534803320049032e-05, + "loss": 3.4681, + "step": 1505792 + }, + { + "epoch": 1.02, + "learning_rate": 2.5339663631783528e-05, + "loss": 3.4768, + "step": 1506304 + }, + { + "epoch": 1.02, + "learning_rate": 2.5331277684273008e-05, + "loss": 3.4688, + "step": 1506816 + }, + { + "epoch": 1.02, + "learning_rate": 2.5322891736762488e-05, + "loss": 3.4739, + "step": 1507328 + }, + { + "epoch": 1.02, + "learning_rate": 2.5314505789251968e-05, + "loss": 3.4764, + "step": 1507840 + }, + { + "epoch": 1.02, + "learning_rate": 2.530613622054518e-05, + "loss": 3.479, + "step": 1508352 + }, + { + "epoch": 1.02, + "learning_rate": 2.529775027303466e-05, + "loss": 3.4889, + "step": 1508864 + }, + { + "epoch": 1.02, + "learning_rate": 2.528936432552414e-05, + "loss": 3.4907, + "step": 1509376 + }, + { + "epoch": 1.02, + "learning_rate": 2.528097837801362e-05, + "loss": 3.4802, + "step": 1509888 + }, + { + "epoch": 1.02, + "learning_rate": 2.527260880930683e-05, + "loss": 3.4724, + "step": 1510400 + }, + { + "epoch": 1.02, + "learning_rate": 2.526422286179631e-05, + "loss": 3.4756, + "step": 1510912 + }, + { + "epoch": 1.02, + "learning_rate": 2.525583691428579e-05, + "loss": 3.479, + "step": 1511424 + }, + { + "epoch": 1.02, + "learning_rate": 2.5247450966775273e-05, + "loss": 3.4688, + "step": 1511936 + }, + { + "epoch": 1.02, + "learning_rate": 2.5239081398068482e-05, + "loss": 3.4766, + "step": 1512448 + }, + { + "epoch": 1.02, + "learning_rate": 2.523069545055796e-05, + "loss": 3.4769, + "step": 1512960 + }, + { + "epoch": 1.02, + "learning_rate": 2.522230950304744e-05, + "loss": 3.4731, + "step": 1513472 + }, + { + "epoch": 1.02, + "learning_rate": 2.521392355553692e-05, + "loss": 3.4699, + "step": 1513984 + }, + { + "epoch": 1.02, + "learning_rate": 2.5205570365633863e-05, + "loss": 3.4743, + "step": 1514496 + }, + { + "epoch": 1.02, + "learning_rate": 2.5197184418123343e-05, + "loss": 3.4689, + "step": 1515008 + }, + { + "epoch": 1.02, + "learning_rate": 2.5188798470612823e-05, + "loss": 3.4744, + "step": 1515520 + }, + { + "epoch": 1.02, + "learning_rate": 2.5180412523102303e-05, + "loss": 3.4669, + "step": 1516032 + }, + { + "epoch": 1.02, + "learning_rate": 2.5172042954395512e-05, + "loss": 3.4904, + "step": 1516544 + }, + { + "epoch": 1.02, + "learning_rate": 2.5163657006884996e-05, + "loss": 3.4883, + "step": 1517056 + }, + { + "epoch": 1.02, + "learning_rate": 2.5155271059374475e-05, + "loss": 3.4843, + "step": 1517568 + }, + { + "epoch": 1.02, + "learning_rate": 2.5146885111863955e-05, + "loss": 3.4637, + "step": 1518080 + }, + { + "epoch": 1.02, + "learning_rate": 2.5138499164353435e-05, + "loss": 3.4778, + "step": 1518592 + }, + { + "epoch": 1.02, + "learning_rate": 2.5130113216842915e-05, + "loss": 3.4827, + "step": 1519104 + }, + { + "epoch": 1.02, + "learning_rate": 2.5121727269332395e-05, + "loss": 3.4787, + "step": 1519616 + }, + { + "epoch": 1.02, + "learning_rate": 2.5113341321821875e-05, + "loss": 3.4775, + "step": 1520128 + }, + { + "epoch": 1.02, + "learning_rate": 2.5104971753115088e-05, + "loss": 3.4783, + "step": 1520640 + }, + { + "epoch": 1.02, + "learning_rate": 2.5096585805604568e-05, + "loss": 3.476, + "step": 1521152 + }, + { + "epoch": 1.02, + "learning_rate": 2.5088199858094048e-05, + "loss": 3.4833, + "step": 1521664 + }, + { + "epoch": 1.02, + "learning_rate": 2.5079813910583528e-05, + "loss": 3.4754, + "step": 1522176 + }, + { + "epoch": 1.02, + "learning_rate": 2.5071460720680466e-05, + "loss": 3.4773, + "step": 1522688 + }, + { + "epoch": 1.02, + "learning_rate": 2.506307477316995e-05, + "loss": 3.4771, + "step": 1523200 + }, + { + "epoch": 1.02, + "learning_rate": 2.505468882565943e-05, + "loss": 3.4661, + "step": 1523712 + }, + { + "epoch": 1.02, + "learning_rate": 2.504630287814891e-05, + "loss": 3.4836, + "step": 1524224 + }, + { + "epoch": 1.02, + "learning_rate": 2.503791693063839e-05, + "loss": 3.4816, + "step": 1524736 + }, + { + "epoch": 1.02, + "learning_rate": 2.502953098312787e-05, + "loss": 3.4788, + "step": 1525248 + }, + { + "epoch": 1.02, + "learning_rate": 2.502114503561735e-05, + "loss": 3.4653, + "step": 1525760 + }, + { + "epoch": 1.02, + "learning_rate": 2.501275908810683e-05, + "loss": 3.4695, + "step": 1526272 + }, + { + "epoch": 1.03, + "eval_loss": 3.8482463359832764, + "eval_runtime": 307.5784, + "eval_samples_per_second": 1240.63, + "eval_steps_per_second": 38.771, + "step": 1526400 + }, + { + "epoch": 0.0, + "learning_rate": 2.500437314059631e-05, + "loss": 3.471, + "step": 1526784 + }, + { + "epoch": 0.0, + "learning_rate": 2.499598719308579e-05, + "loss": 3.4703, + "step": 1527296 + }, + { + "epoch": 0.0, + "learning_rate": 2.498760124557527e-05, + "loss": 3.4771, + "step": 1527808 + }, + { + "epoch": 0.0, + "learning_rate": 2.497921529806475e-05, + "loss": 3.4764, + "step": 1528320 + }, + { + "epoch": 0.0, + "learning_rate": 2.497086210816169e-05, + "loss": 3.4931, + "step": 1528832 + }, + { + "epoch": 0.0, + "learning_rate": 2.496247616065117e-05, + "loss": 3.4703, + "step": 1529344 + }, + { + "epoch": 0.0, + "learning_rate": 2.495409021314065e-05, + "loss": 3.4702, + "step": 1529856 + }, + { + "epoch": 0.0, + "learning_rate": 2.494570426563013e-05, + "loss": 3.4572, + "step": 1530368 + }, + { + "epoch": 0.0, + "learning_rate": 2.493731831811961e-05, + "loss": 3.4773, + "step": 1530880 + }, + { + "epoch": 0.0, + "learning_rate": 2.492893237060909e-05, + "loss": 3.4765, + "step": 1531392 + }, + { + "epoch": 0.0, + "learning_rate": 2.492054642309857e-05, + "loss": 3.4748, + "step": 1531904 + }, + { + "epoch": 0.0, + "learning_rate": 2.491216047558805e-05, + "loss": 3.479, + "step": 1532416 + }, + { + "epoch": 0.0, + "learning_rate": 2.490379090688126e-05, + "loss": 3.467, + "step": 1532928 + }, + { + "epoch": 0.0, + "learning_rate": 2.4895404959370743e-05, + "loss": 3.4706, + "step": 1533440 + }, + { + "epoch": 0.0, + "learning_rate": 2.4887019011860222e-05, + "loss": 3.4617, + "step": 1533952 + }, + { + "epoch": 0.0, + "learning_rate": 2.487864944315343e-05, + "loss": 3.471, + "step": 1534464 + }, + { + "epoch": 0.0, + "learning_rate": 2.487026349564291e-05, + "loss": 3.4643, + "step": 1534976 + }, + { + "epoch": 0.0, + "learning_rate": 2.486187754813239e-05, + "loss": 3.4658, + "step": 1535488 + }, + { + "epoch": 0.0, + "learning_rate": 2.485349160062187e-05, + "loss": 3.469, + "step": 1536000 + }, + { + "epoch": 0.0, + "learning_rate": 2.484510565311135e-05, + "loss": 3.4906, + "step": 1536512 + }, + { + "epoch": 0.0, + "learning_rate": 2.483671970560083e-05, + "loss": 3.4699, + "step": 1537024 + }, + { + "epoch": 0.0, + "learning_rate": 2.482833375809031e-05, + "loss": 3.4742, + "step": 1537536 + }, + { + "epoch": 0.0, + "learning_rate": 2.481994781057979e-05, + "loss": 3.47, + "step": 1538048 + }, + { + "epoch": 0.0, + "learning_rate": 2.4811578241873e-05, + "loss": 3.4783, + "step": 1538560 + }, + { + "epoch": 0.0, + "learning_rate": 2.480319229436248e-05, + "loss": 3.4671, + "step": 1539072 + }, + { + "epoch": 0.0, + "learning_rate": 2.4794806346851964e-05, + "loss": 3.4756, + "step": 1539584 + }, + { + "epoch": 0.0, + "learning_rate": 2.4786420399341444e-05, + "loss": 3.4684, + "step": 1540096 + }, + { + "epoch": 0.0, + "learning_rate": 2.4778067209438385e-05, + "loss": 3.4648, + "step": 1540608 + }, + { + "epoch": 0.0, + "learning_rate": 2.4769681261927865e-05, + "loss": 3.4577, + "step": 1541120 + }, + { + "epoch": 0.0, + "learning_rate": 2.4761295314417345e-05, + "loss": 3.4641, + "step": 1541632 + }, + { + "epoch": 0.01, + "learning_rate": 2.4752909366906825e-05, + "loss": 3.4708, + "step": 1542144 + }, + { + "epoch": 0.01, + "learning_rate": 2.4744523419396305e-05, + "loss": 3.4744, + "step": 1542656 + }, + { + "epoch": 0.01, + "learning_rate": 2.4736137471885785e-05, + "loss": 3.4796, + "step": 1543168 + }, + { + "epoch": 0.01, + "learning_rate": 2.4727751524375265e-05, + "loss": 3.4756, + "step": 1543680 + }, + { + "epoch": 0.01, + "learning_rate": 2.4719365576864745e-05, + "loss": 3.4658, + "step": 1544192 + }, + { + "epoch": 0.01, + "learning_rate": 2.4710996008157954e-05, + "loss": 3.4792, + "step": 1544704 + }, + { + "epoch": 0.01, + "learning_rate": 2.4702626439451166e-05, + "loss": 3.4691, + "step": 1545216 + }, + { + "epoch": 0.01, + "learning_rate": 2.469424049194065e-05, + "loss": 3.469, + "step": 1545728 + }, + { + "epoch": 0.01, + "learning_rate": 2.4685854544430126e-05, + "loss": 3.4542, + "step": 1546240 + }, + { + "epoch": 0.01, + "learning_rate": 2.4677468596919606e-05, + "loss": 3.4706, + "step": 1546752 + }, + { + "epoch": 0.01, + "learning_rate": 2.4669082649409086e-05, + "loss": 3.4675, + "step": 1547264 + }, + { + "epoch": 0.01, + "learning_rate": 2.4660696701898566e-05, + "loss": 3.4773, + "step": 1547776 + }, + { + "epoch": 0.01, + "learning_rate": 2.4652310754388046e-05, + "loss": 3.4697, + "step": 1548288 + }, + { + "epoch": 0.01, + "learning_rate": 2.4643924806877526e-05, + "loss": 3.4621, + "step": 1548800 + }, + { + "epoch": 0.01, + "learning_rate": 2.463555523817074e-05, + "loss": 3.478, + "step": 1549312 + }, + { + "epoch": 0.01, + "learning_rate": 2.462716929066022e-05, + "loss": 3.4683, + "step": 1549824 + }, + { + "epoch": 0.01, + "learning_rate": 2.46187833431497e-05, + "loss": 3.4632, + "step": 1550336 + }, + { + "epoch": 0.01, + "learning_rate": 2.461039739563918e-05, + "loss": 3.4551, + "step": 1550848 + }, + { + "epoch": 0.01, + "learning_rate": 2.460204420573612e-05, + "loss": 3.4566, + "step": 1551360 + }, + { + "epoch": 0.01, + "learning_rate": 2.45936582582256e-05, + "loss": 3.4726, + "step": 1551872 + }, + { + "epoch": 0.01, + "learning_rate": 2.458527231071508e-05, + "loss": 3.4661, + "step": 1552384 + }, + { + "epoch": 0.01, + "learning_rate": 2.457688636320456e-05, + "loss": 3.4666, + "step": 1552896 + }, + { + "epoch": 0.01, + "learning_rate": 2.456850041569404e-05, + "loss": 3.4585, + "step": 1553408 + }, + { + "epoch": 0.01, + "learning_rate": 2.456013084698725e-05, + "loss": 3.4646, + "step": 1553920 + }, + { + "epoch": 0.01, + "learning_rate": 2.455174489947673e-05, + "loss": 3.4534, + "step": 1554432 + }, + { + "epoch": 0.01, + "learning_rate": 2.4543358951966212e-05, + "loss": 3.4725, + "step": 1554944 + }, + { + "epoch": 0.01, + "learning_rate": 2.4534973004455692e-05, + "loss": 3.4585, + "step": 1555456 + }, + { + "epoch": 0.01, + "learning_rate": 2.4526587056945172e-05, + "loss": 3.4717, + "step": 1555968 + }, + { + "epoch": 0.01, + "learning_rate": 2.4518201109434652e-05, + "loss": 3.4655, + "step": 1556480 + }, + { + "epoch": 0.01, + "learning_rate": 2.450981516192413e-05, + "loss": 3.4635, + "step": 1556992 + }, + { + "epoch": 0.01, + "learning_rate": 2.450142921441361e-05, + "loss": 3.4577, + "step": 1557504 + }, + { + "epoch": 0.01, + "learning_rate": 2.449305964570682e-05, + "loss": 3.468, + "step": 1558016 + }, + { + "epoch": 0.01, + "learning_rate": 2.44846736981963e-05, + "loss": 3.4564, + "step": 1558528 + }, + { + "epoch": 0.01, + "learning_rate": 2.447628775068578e-05, + "loss": 3.4648, + "step": 1559040 + }, + { + "epoch": 0.01, + "learning_rate": 2.446790180317526e-05, + "loss": 3.4711, + "step": 1559552 + }, + { + "epoch": 0.01, + "learning_rate": 2.4459532234468474e-05, + "loss": 3.4691, + "step": 1560064 + }, + { + "epoch": 0.01, + "learning_rate": 2.445114628695795e-05, + "loss": 3.4557, + "step": 1560576 + }, + { + "epoch": 0.01, + "learning_rate": 2.4442760339447434e-05, + "loss": 3.4595, + "step": 1561088 + }, + { + "epoch": 0.01, + "learning_rate": 2.4434390770740646e-05, + "loss": 3.4588, + "step": 1561600 + }, + { + "epoch": 0.01, + "learning_rate": 2.4426004823230126e-05, + "loss": 3.4583, + "step": 1562112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4417618875719603e-05, + "loss": 3.4716, + "step": 1562624 + }, + { + "epoch": 0.01, + "learning_rate": 2.4409232928209082e-05, + "loss": 3.464, + "step": 1563136 + }, + { + "epoch": 0.01, + "learning_rate": 2.4400863359502295e-05, + "loss": 3.4797, + "step": 1563648 + }, + { + "epoch": 0.01, + "learning_rate": 2.4392477411991775e-05, + "loss": 3.4725, + "step": 1564160 + }, + { + "epoch": 0.01, + "learning_rate": 2.4384091464481255e-05, + "loss": 3.4761, + "step": 1564672 + }, + { + "epoch": 0.01, + "learning_rate": 2.4375705516970735e-05, + "loss": 3.4589, + "step": 1565184 + }, + { + "epoch": 0.01, + "learning_rate": 2.4367319569460215e-05, + "loss": 3.467, + "step": 1565696 + }, + { + "epoch": 0.01, + "learning_rate": 2.4358933621949695e-05, + "loss": 3.4784, + "step": 1566208 + }, + { + "epoch": 0.01, + "learning_rate": 2.4350564053242904e-05, + "loss": 3.4639, + "step": 1566720 + }, + { + "epoch": 0.01, + "learning_rate": 2.4342178105732387e-05, + "loss": 3.4665, + "step": 1567232 + }, + { + "epoch": 0.01, + "learning_rate": 2.4333792158221867e-05, + "loss": 3.467, + "step": 1567744 + }, + { + "epoch": 0.01, + "learning_rate": 2.4325406210711347e-05, + "loss": 3.4824, + "step": 1568256 + }, + { + "epoch": 0.01, + "learning_rate": 2.4317020263200827e-05, + "loss": 3.4652, + "step": 1568768 + }, + { + "epoch": 0.01, + "learning_rate": 2.4308634315690307e-05, + "loss": 3.4511, + "step": 1569280 + }, + { + "epoch": 0.01, + "learning_rate": 2.4300248368179784e-05, + "loss": 3.461, + "step": 1569792 + }, + { + "epoch": 0.01, + "learning_rate": 2.4291862420669264e-05, + "loss": 3.4661, + "step": 1570304 + }, + { + "epoch": 0.01, + "learning_rate": 2.4283492851962476e-05, + "loss": 3.4718, + "step": 1570816 + }, + { + "epoch": 0.01, + "learning_rate": 2.4275106904451956e-05, + "loss": 3.4695, + "step": 1571328 + }, + { + "epoch": 0.01, + "learning_rate": 2.4266720956941436e-05, + "loss": 3.4606, + "step": 1571840 + }, + { + "epoch": 0.02, + "learning_rate": 2.4258335009430916e-05, + "loss": 3.4639, + "step": 1572352 + }, + { + "epoch": 0.02, + "learning_rate": 2.424996544072413e-05, + "loss": 3.4593, + "step": 1572864 + }, + { + "epoch": 0.02, + "learning_rate": 2.4241579493213605e-05, + "loss": 3.4578, + "step": 1573376 + }, + { + "epoch": 0.02, + "learning_rate": 2.4233193545703088e-05, + "loss": 3.4627, + "step": 1573888 + }, + { + "epoch": 0.02, + "learning_rate": 2.42248239769963e-05, + "loss": 3.4742, + "step": 1574400 + }, + { + "epoch": 0.02, + "learning_rate": 2.421643802948578e-05, + "loss": 3.4865, + "step": 1574912 + }, + { + "epoch": 0.02, + "learning_rate": 2.4208052081975257e-05, + "loss": 3.4693, + "step": 1575424 + }, + { + "epoch": 0.02, + "learning_rate": 2.4199666134464737e-05, + "loss": 3.4541, + "step": 1575936 + }, + { + "epoch": 0.02, + "learning_rate": 2.4191280186954217e-05, + "loss": 3.4714, + "step": 1576448 + }, + { + "epoch": 0.02, + "learning_rate": 2.4182894239443697e-05, + "loss": 3.4583, + "step": 1576960 + }, + { + "epoch": 0.02, + "learning_rate": 2.417450829193318e-05, + "loss": 3.4748, + "step": 1577472 + }, + { + "epoch": 0.02, + "learning_rate": 2.416612234442266e-05, + "loss": 3.4686, + "step": 1577984 + }, + { + "epoch": 0.02, + "learning_rate": 2.415775277571587e-05, + "loss": 3.4667, + "step": 1578496 + }, + { + "epoch": 0.02, + "learning_rate": 2.414936682820535e-05, + "loss": 3.4636, + "step": 1579008 + }, + { + "epoch": 0.02, + "learning_rate": 2.414098088069483e-05, + "loss": 3.4722, + "step": 1579520 + }, + { + "epoch": 0.02, + "learning_rate": 2.413259493318431e-05, + "loss": 3.4536, + "step": 1580032 + }, + { + "epoch": 0.02, + "learning_rate": 2.4124225364477522e-05, + "loss": 3.4637, + "step": 1580544 + }, + { + "epoch": 0.02, + "learning_rate": 2.4115839416967002e-05, + "loss": 3.4542, + "step": 1581056 + }, + { + "epoch": 0.02, + "learning_rate": 2.4107453469456482e-05, + "loss": 3.4735, + "step": 1581568 + }, + { + "epoch": 0.02, + "learning_rate": 2.4099067521945962e-05, + "loss": 3.4568, + "step": 1582080 + }, + { + "epoch": 0.02, + "learning_rate": 2.409069795323917e-05, + "loss": 3.4616, + "step": 1582592 + }, + { + "epoch": 0.02, + "learning_rate": 2.408231200572865e-05, + "loss": 3.4574, + "step": 1583104 + }, + { + "epoch": 0.02, + "learning_rate": 2.4073942437021863e-05, + "loss": 3.4657, + "step": 1583616 + }, + { + "epoch": 0.02, + "learning_rate": 2.4065556489511343e-05, + "loss": 3.4663, + "step": 1584128 + }, + { + "epoch": 0.02, + "learning_rate": 2.4057170542000823e-05, + "loss": 3.4634, + "step": 1584640 + }, + { + "epoch": 0.02, + "learning_rate": 2.4048784594490303e-05, + "loss": 3.4763, + "step": 1585152 + }, + { + "epoch": 0.02, + "learning_rate": 2.4040398646979783e-05, + "loss": 3.4776, + "step": 1585664 + }, + { + "epoch": 0.02, + "learning_rate": 2.403201269946926e-05, + "loss": 3.4686, + "step": 1586176 + }, + { + "epoch": 0.02, + "learning_rate": 2.4023626751958743e-05, + "loss": 3.4627, + "step": 1586688 + }, + { + "epoch": 0.02, + "learning_rate": 2.4015240804448223e-05, + "loss": 3.4635, + "step": 1587200 + }, + { + "epoch": 0.02, + "learning_rate": 2.4006871235741435e-05, + "loss": 3.4713, + "step": 1587712 + }, + { + "epoch": 0.02, + "learning_rate": 2.3998485288230912e-05, + "loss": 3.4523, + "step": 1588224 + }, + { + "epoch": 0.02, + "learning_rate": 2.3990099340720392e-05, + "loss": 3.4655, + "step": 1588736 + }, + { + "epoch": 0.02, + "learning_rate": 2.3981713393209872e-05, + "loss": 3.4591, + "step": 1589248 + }, + { + "epoch": 0.02, + "learning_rate": 2.3973343824503084e-05, + "loss": 3.4652, + "step": 1589760 + }, + { + "epoch": 0.02, + "learning_rate": 2.3964957876992564e-05, + "loss": 3.4604, + "step": 1590272 + }, + { + "epoch": 0.02, + "learning_rate": 2.3956571929482044e-05, + "loss": 3.4618, + "step": 1590784 + }, + { + "epoch": 0.02, + "learning_rate": 2.3948185981971524e-05, + "loss": 3.4554, + "step": 1591296 + }, + { + "epoch": 0.02, + "learning_rate": 2.3939816413264733e-05, + "loss": 3.4647, + "step": 1591808 + }, + { + "epoch": 0.02, + "learning_rate": 2.3931430465754213e-05, + "loss": 3.4559, + "step": 1592320 + }, + { + "epoch": 0.02, + "learning_rate": 2.3923044518243697e-05, + "loss": 3.4751, + "step": 1592832 + }, + { + "epoch": 0.02, + "learning_rate": 2.391467494953691e-05, + "loss": 3.47, + "step": 1593344 + }, + { + "epoch": 0.02, + "learning_rate": 2.3906289002026386e-05, + "loss": 3.479, + "step": 1593856 + }, + { + "epoch": 0.02, + "learning_rate": 2.3897903054515866e-05, + "loss": 3.4504, + "step": 1594368 + }, + { + "epoch": 0.02, + "learning_rate": 2.3889517107005346e-05, + "loss": 3.4676, + "step": 1594880 + }, + { + "epoch": 0.02, + "learning_rate": 2.3881131159494826e-05, + "loss": 3.4705, + "step": 1595392 + }, + { + "epoch": 0.02, + "learning_rate": 2.3872745211984306e-05, + "loss": 3.465, + "step": 1595904 + }, + { + "epoch": 0.02, + "learning_rate": 2.386435926447379e-05, + "loss": 3.4659, + "step": 1596416 + }, + { + "epoch": 0.02, + "learning_rate": 2.3855989695766998e-05, + "loss": 3.4668, + "step": 1596928 + }, + { + "epoch": 0.02, + "learning_rate": 2.3847603748256478e-05, + "loss": 3.4621, + "step": 1597440 + }, + { + "epoch": 0.02, + "learning_rate": 2.3839217800745958e-05, + "loss": 3.4713, + "step": 1597952 + }, + { + "epoch": 0.02, + "learning_rate": 2.3830831853235438e-05, + "loss": 3.4593, + "step": 1598464 + }, + { + "epoch": 0.02, + "learning_rate": 2.382246228452865e-05, + "loss": 3.4673, + "step": 1598976 + }, + { + "epoch": 0.02, + "learning_rate": 2.381409271582186e-05, + "loss": 3.4634, + "step": 1599488 + }, + { + "epoch": 0.02, + "learning_rate": 2.380570676831134e-05, + "loss": 3.458, + "step": 1600000 + }, + { + "epoch": 0.02, + "learning_rate": 2.379732082080082e-05, + "loss": 3.4652, + "step": 1600512 + }, + { + "epoch": 0.02, + "learning_rate": 2.37889348732903e-05, + "loss": 3.4757, + "step": 1601024 + }, + { + "epoch": 0.02, + "learning_rate": 2.378054892577978e-05, + "loss": 3.4653, + "step": 1601536 + }, + { + "epoch": 0.02, + "learning_rate": 2.377216297826926e-05, + "loss": 3.4514, + "step": 1602048 + }, + { + "epoch": 0.02, + "learning_rate": 2.376377703075874e-05, + "loss": 3.4604, + "step": 1602560 + }, + { + "epoch": 0.03, + "eval_loss": 3.849696159362793, + "eval_runtime": 302.9187, + "eval_samples_per_second": 1259.714, + "eval_steps_per_second": 39.367, + "step": 1602720 + }, + { + "epoch": 0.0, + "learning_rate": 2.375539108324822e-05, + "loss": 3.4598, + "step": 1603072 + }, + { + "epoch": 0.0, + "learning_rate": 2.37470051357377e-05, + "loss": 3.4585, + "step": 1603584 + }, + { + "epoch": 0.0, + "learning_rate": 2.373861918822718e-05, + "loss": 3.4654, + "step": 1604096 + }, + { + "epoch": 0.0, + "learning_rate": 2.373023324071666e-05, + "loss": 3.4683, + "step": 1604608 + }, + { + "epoch": 0.0, + "learning_rate": 2.3721880050813604e-05, + "loss": 3.4782, + "step": 1605120 + }, + { + "epoch": 0.0, + "learning_rate": 2.3713494103303084e-05, + "loss": 3.4639, + "step": 1605632 + }, + { + "epoch": 0.0, + "learning_rate": 2.370510815579256e-05, + "loss": 3.4564, + "step": 1606144 + }, + { + "epoch": 0.0, + "learning_rate": 2.369672220828204e-05, + "loss": 3.4484, + "step": 1606656 + }, + { + "epoch": 0.0, + "learning_rate": 2.368833626077152e-05, + "loss": 3.4643, + "step": 1607168 + }, + { + "epoch": 0.0, + "learning_rate": 2.3679950313261e-05, + "loss": 3.4675, + "step": 1607680 + }, + { + "epoch": 0.0, + "learning_rate": 2.367156436575048e-05, + "loss": 3.4612, + "step": 1608192 + }, + { + "epoch": 0.0, + "learning_rate": 2.366317841823996e-05, + "loss": 3.4659, + "step": 1608704 + }, + { + "epoch": 0.0, + "learning_rate": 2.3654808849533173e-05, + "loss": 3.4559, + "step": 1609216 + }, + { + "epoch": 0.0, + "learning_rate": 2.3646422902022653e-05, + "loss": 3.46, + "step": 1609728 + }, + { + "epoch": 0.0, + "learning_rate": 2.3638036954512133e-05, + "loss": 3.4518, + "step": 1610240 + }, + { + "epoch": 0.0, + "learning_rate": 2.3629667385805342e-05, + "loss": 3.4612, + "step": 1610752 + }, + { + "epoch": 0.0, + "learning_rate": 2.3621281438294822e-05, + "loss": 3.4493, + "step": 1611264 + }, + { + "epoch": 0.0, + "learning_rate": 2.3612895490784305e-05, + "loss": 3.4585, + "step": 1611776 + }, + { + "epoch": 0.0, + "learning_rate": 2.3604509543273785e-05, + "loss": 3.4549, + "step": 1612288 + }, + { + "epoch": 0.0, + "learning_rate": 2.3596123595763265e-05, + "loss": 3.4745, + "step": 1612800 + }, + { + "epoch": 0.0, + "learning_rate": 2.358773764825274e-05, + "loss": 3.4613, + "step": 1613312 + }, + { + "epoch": 0.0, + "learning_rate": 2.357935170074222e-05, + "loss": 3.4655, + "step": 1613824 + }, + { + "epoch": 0.0, + "learning_rate": 2.35709657532317e-05, + "loss": 3.4564, + "step": 1614336 + }, + { + "epoch": 0.0, + "learning_rate": 2.3562596184524914e-05, + "loss": 3.4685, + "step": 1614848 + }, + { + "epoch": 0.0, + "learning_rate": 2.3554210237014394e-05, + "loss": 3.4517, + "step": 1615360 + }, + { + "epoch": 0.0, + "learning_rate": 2.3545824289503874e-05, + "loss": 3.4659, + "step": 1615872 + }, + { + "epoch": 0.0, + "learning_rate": 2.3537438341993354e-05, + "loss": 3.4618, + "step": 1616384 + }, + { + "epoch": 0.0, + "learning_rate": 2.3529085152090296e-05, + "loss": 3.4486, + "step": 1616896 + }, + { + "epoch": 0.0, + "learning_rate": 2.3520699204579775e-05, + "loss": 3.4451, + "step": 1617408 + }, + { + "epoch": 0.0, + "learning_rate": 2.351231325706926e-05, + "loss": 3.4519, + "step": 1617920 + }, + { + "epoch": 0.01, + "learning_rate": 2.350392730955874e-05, + "loss": 3.4603, + "step": 1618432 + }, + { + "epoch": 0.01, + "learning_rate": 2.3495541362048215e-05, + "loss": 3.461, + "step": 1618944 + }, + { + "epoch": 0.01, + "learning_rate": 2.3487155414537695e-05, + "loss": 3.4658, + "step": 1619456 + }, + { + "epoch": 0.01, + "learning_rate": 2.3478769467027175e-05, + "loss": 3.4674, + "step": 1619968 + }, + { + "epoch": 0.01, + "learning_rate": 2.3470383519516655e-05, + "loss": 3.4549, + "step": 1620480 + }, + { + "epoch": 0.01, + "learning_rate": 2.3462013950809868e-05, + "loss": 3.4651, + "step": 1620992 + }, + { + "epoch": 0.01, + "learning_rate": 2.345364438210308e-05, + "loss": 3.4599, + "step": 1621504 + }, + { + "epoch": 0.01, + "learning_rate": 2.344525843459256e-05, + "loss": 3.4594, + "step": 1622016 + }, + { + "epoch": 0.01, + "learning_rate": 2.343687248708204e-05, + "loss": 3.4427, + "step": 1622528 + }, + { + "epoch": 0.01, + "learning_rate": 2.3428486539571517e-05, + "loss": 3.4599, + "step": 1623040 + }, + { + "epoch": 0.01, + "learning_rate": 2.3420100592060997e-05, + "loss": 3.4551, + "step": 1623552 + }, + { + "epoch": 0.01, + "learning_rate": 2.3411714644550477e-05, + "loss": 3.4649, + "step": 1624064 + }, + { + "epoch": 0.01, + "learning_rate": 2.340332869703996e-05, + "loss": 3.4582, + "step": 1624576 + }, + { + "epoch": 0.01, + "learning_rate": 2.339494274952944e-05, + "loss": 3.453, + "step": 1625088 + }, + { + "epoch": 0.01, + "learning_rate": 2.338657318082265e-05, + "loss": 3.4655, + "step": 1625600 + }, + { + "epoch": 0.01, + "learning_rate": 2.337818723331213e-05, + "loss": 3.4529, + "step": 1626112 + }, + { + "epoch": 0.01, + "learning_rate": 2.336980128580161e-05, + "loss": 3.4528, + "step": 1626624 + }, + { + "epoch": 0.01, + "learning_rate": 2.336141533829109e-05, + "loss": 3.4453, + "step": 1627136 + }, + { + "epoch": 0.01, + "learning_rate": 2.3353062148388034e-05, + "loss": 3.4458, + "step": 1627648 + }, + { + "epoch": 0.01, + "learning_rate": 2.3344676200877514e-05, + "loss": 3.4599, + "step": 1628160 + }, + { + "epoch": 0.01, + "learning_rate": 2.333629025336699e-05, + "loss": 3.4575, + "step": 1628672 + }, + { + "epoch": 0.01, + "learning_rate": 2.332790430585647e-05, + "loss": 3.4529, + "step": 1629184 + }, + { + "epoch": 0.01, + "learning_rate": 2.331951835834595e-05, + "loss": 3.4493, + "step": 1629696 + }, + { + "epoch": 0.01, + "learning_rate": 2.3311148789639163e-05, + "loss": 3.4554, + "step": 1630208 + }, + { + "epoch": 0.01, + "learning_rate": 2.3302762842128643e-05, + "loss": 3.4362, + "step": 1630720 + }, + { + "epoch": 0.01, + "learning_rate": 2.3294376894618123e-05, + "loss": 3.4623, + "step": 1631232 + }, + { + "epoch": 0.01, + "learning_rate": 2.3285990947107603e-05, + "loss": 3.4487, + "step": 1631744 + }, + { + "epoch": 0.01, + "learning_rate": 2.3277604999597083e-05, + "loss": 3.4572, + "step": 1632256 + }, + { + "epoch": 0.01, + "learning_rate": 2.3269219052086563e-05, + "loss": 3.4525, + "step": 1632768 + }, + { + "epoch": 0.01, + "learning_rate": 2.3260833104576042e-05, + "loss": 3.4545, + "step": 1633280 + }, + { + "epoch": 0.01, + "learning_rate": 2.3252447157065522e-05, + "loss": 3.4459, + "step": 1633792 + }, + { + "epoch": 0.01, + "learning_rate": 2.3244077588358735e-05, + "loss": 3.4558, + "step": 1634304 + }, + { + "epoch": 0.01, + "learning_rate": 2.3235691640848215e-05, + "loss": 3.4482, + "step": 1634816 + }, + { + "epoch": 0.01, + "learning_rate": 2.322730569333769e-05, + "loss": 3.4499, + "step": 1635328 + }, + { + "epoch": 0.01, + "learning_rate": 2.321891974582717e-05, + "loss": 3.461, + "step": 1635840 + }, + { + "epoch": 0.01, + "learning_rate": 2.3210550177120384e-05, + "loss": 3.4566, + "step": 1636352 + }, + { + "epoch": 0.01, + "learning_rate": 2.3202164229609867e-05, + "loss": 3.4414, + "step": 1636864 + }, + { + "epoch": 0.01, + "learning_rate": 2.3193778282099344e-05, + "loss": 3.4512, + "step": 1637376 + }, + { + "epoch": 0.01, + "learning_rate": 2.3185392334588824e-05, + "loss": 3.4439, + "step": 1637888 + }, + { + "epoch": 0.01, + "learning_rate": 2.3177006387078304e-05, + "loss": 3.4438, + "step": 1638400 + }, + { + "epoch": 0.01, + "learning_rate": 2.3168620439567784e-05, + "loss": 3.4608, + "step": 1638912 + }, + { + "epoch": 0.01, + "learning_rate": 2.3160234492057264e-05, + "loss": 3.4546, + "step": 1639424 + }, + { + "epoch": 0.01, + "learning_rate": 2.315188130215421e-05, + "loss": 3.4631, + "step": 1639936 + }, + { + "epoch": 0.01, + "learning_rate": 2.314349535464369e-05, + "loss": 3.4581, + "step": 1640448 + }, + { + "epoch": 0.01, + "learning_rate": 2.3135109407133165e-05, + "loss": 3.4699, + "step": 1640960 + }, + { + "epoch": 0.01, + "learning_rate": 2.3126723459622645e-05, + "loss": 3.4506, + "step": 1641472 + }, + { + "epoch": 0.01, + "learning_rate": 2.3118337512112125e-05, + "loss": 3.4525, + "step": 1641984 + }, + { + "epoch": 0.01, + "learning_rate": 2.3109967943405338e-05, + "loss": 3.4646, + "step": 1642496 + }, + { + "epoch": 0.01, + "learning_rate": 2.3101581995894818e-05, + "loss": 3.4509, + "step": 1643008 + }, + { + "epoch": 0.01, + "learning_rate": 2.3093196048384297e-05, + "loss": 3.4586, + "step": 1643520 + }, + { + "epoch": 0.01, + "learning_rate": 2.3084810100873777e-05, + "loss": 3.4601, + "step": 1644032 + }, + { + "epoch": 0.01, + "learning_rate": 2.3076424153363257e-05, + "loss": 3.4642, + "step": 1644544 + }, + { + "epoch": 0.01, + "learning_rate": 2.3068054584656466e-05, + "loss": 3.4534, + "step": 1645056 + }, + { + "epoch": 0.01, + "learning_rate": 2.3059668637145946e-05, + "loss": 3.4423, + "step": 1645568 + }, + { + "epoch": 0.01, + "learning_rate": 2.305128268963543e-05, + "loss": 3.4479, + "step": 1646080 + }, + { + "epoch": 0.01, + "learning_rate": 2.304289674212491e-05, + "loss": 3.4537, + "step": 1646592 + }, + { + "epoch": 0.01, + "learning_rate": 2.303451079461439e-05, + "loss": 3.461, + "step": 1647104 + }, + { + "epoch": 0.01, + "learning_rate": 2.302612484710387e-05, + "loss": 3.458, + "step": 1647616 + }, + { + "epoch": 0.01, + "learning_rate": 2.3017738899593346e-05, + "loss": 3.4509, + "step": 1648128 + }, + { + "epoch": 0.02, + "learning_rate": 2.3009352952082826e-05, + "loss": 3.454, + "step": 1648640 + }, + { + "epoch": 0.02, + "learning_rate": 2.300098338337604e-05, + "loss": 3.4473, + "step": 1649152 + }, + { + "epoch": 0.02, + "learning_rate": 2.2992597435865522e-05, + "loss": 3.4451, + "step": 1649664 + }, + { + "epoch": 0.02, + "learning_rate": 2.2984211488355e-05, + "loss": 3.4481, + "step": 1650176 + }, + { + "epoch": 0.02, + "learning_rate": 2.297582554084448e-05, + "loss": 3.4642, + "step": 1650688 + }, + { + "epoch": 0.02, + "learning_rate": 2.296745597213769e-05, + "loss": 3.4776, + "step": 1651200 + }, + { + "epoch": 0.02, + "learning_rate": 2.295907002462717e-05, + "loss": 3.46, + "step": 1651712 + }, + { + "epoch": 0.02, + "learning_rate": 2.295068407711665e-05, + "loss": 3.4422, + "step": 1652224 + }, + { + "epoch": 0.02, + "learning_rate": 2.294229812960613e-05, + "loss": 3.4614, + "step": 1652736 + }, + { + "epoch": 0.02, + "learning_rate": 2.293391218209561e-05, + "loss": 3.4483, + "step": 1653248 + }, + { + "epoch": 0.02, + "learning_rate": 2.292552623458509e-05, + "loss": 3.4609, + "step": 1653760 + }, + { + "epoch": 0.02, + "learning_rate": 2.291714028707457e-05, + "loss": 3.4553, + "step": 1654272 + }, + { + "epoch": 0.02, + "learning_rate": 2.290877071836778e-05, + "loss": 3.4559, + "step": 1654784 + }, + { + "epoch": 0.02, + "learning_rate": 2.290038477085726e-05, + "loss": 3.4529, + "step": 1655296 + }, + { + "epoch": 0.02, + "learning_rate": 2.289199882334674e-05, + "loss": 3.457, + "step": 1655808 + }, + { + "epoch": 0.02, + "learning_rate": 2.2883612875836223e-05, + "loss": 3.4473, + "step": 1656320 + }, + { + "epoch": 0.02, + "learning_rate": 2.2875243307129432e-05, + "loss": 3.4513, + "step": 1656832 + }, + { + "epoch": 0.02, + "learning_rate": 2.2866857359618912e-05, + "loss": 3.4414, + "step": 1657344 + }, + { + "epoch": 0.02, + "learning_rate": 2.2858471412108392e-05, + "loss": 3.4637, + "step": 1657856 + }, + { + "epoch": 0.02, + "learning_rate": 2.2850085464597872e-05, + "loss": 3.4455, + "step": 1658368 + }, + { + "epoch": 0.02, + "learning_rate": 2.2841715895891085e-05, + "loss": 3.4496, + "step": 1658880 + }, + { + "epoch": 0.02, + "learning_rate": 2.2833329948380564e-05, + "loss": 3.4427, + "step": 1659392 + }, + { + "epoch": 0.02, + "learning_rate": 2.2824960379673774e-05, + "loss": 3.4551, + "step": 1659904 + }, + { + "epoch": 0.02, + "learning_rate": 2.2816574432163254e-05, + "loss": 3.4544, + "step": 1660416 + }, + { + "epoch": 0.02, + "learning_rate": 2.2808188484652733e-05, + "loss": 3.4537, + "step": 1660928 + }, + { + "epoch": 0.02, + "learning_rate": 2.2799802537142213e-05, + "loss": 3.4651, + "step": 1661440 + }, + { + "epoch": 0.02, + "learning_rate": 2.2791416589631693e-05, + "loss": 3.4678, + "step": 1661952 + }, + { + "epoch": 0.02, + "learning_rate": 2.2783030642121177e-05, + "loss": 3.4566, + "step": 1662464 + }, + { + "epoch": 0.02, + "learning_rate": 2.2774644694610653e-05, + "loss": 3.4525, + "step": 1662976 + }, + { + "epoch": 0.02, + "learning_rate": 2.2766258747100133e-05, + "loss": 3.4482, + "step": 1663488 + }, + { + "epoch": 0.02, + "learning_rate": 2.2757889178393346e-05, + "loss": 3.4609, + "step": 1664000 + }, + { + "epoch": 0.02, + "learning_rate": 2.2749503230882826e-05, + "loss": 3.4427, + "step": 1664512 + }, + { + "epoch": 0.02, + "learning_rate": 2.2741117283372306e-05, + "loss": 3.4527, + "step": 1665024 + }, + { + "epoch": 0.02, + "learning_rate": 2.2732731335861786e-05, + "loss": 3.447, + "step": 1665536 + }, + { + "epoch": 0.02, + "learning_rate": 2.2724378145958727e-05, + "loss": 3.4565, + "step": 1666048 + }, + { + "epoch": 0.02, + "learning_rate": 2.2715992198448207e-05, + "loss": 3.4418, + "step": 1666560 + }, + { + "epoch": 0.02, + "learning_rate": 2.2707606250937687e-05, + "loss": 3.4508, + "step": 1667072 + }, + { + "epoch": 0.02, + "learning_rate": 2.2699220303427167e-05, + "loss": 3.4506, + "step": 1667584 + }, + { + "epoch": 0.02, + "learning_rate": 2.2690834355916647e-05, + "loss": 3.4486, + "step": 1668096 + }, + { + "epoch": 0.02, + "learning_rate": 2.2682448408406127e-05, + "loss": 3.447, + "step": 1668608 + }, + { + "epoch": 0.02, + "learning_rate": 2.2674062460895607e-05, + "loss": 3.4611, + "step": 1669120 + }, + { + "epoch": 0.02, + "learning_rate": 2.266569289218882e-05, + "loss": 3.4604, + "step": 1669632 + }, + { + "epoch": 0.02, + "learning_rate": 2.2657306944678296e-05, + "loss": 3.4658, + "step": 1670144 + }, + { + "epoch": 0.02, + "learning_rate": 2.2648920997167776e-05, + "loss": 3.4386, + "step": 1670656 + }, + { + "epoch": 0.02, + "learning_rate": 2.264053504965726e-05, + "loss": 3.4567, + "step": 1671168 + }, + { + "epoch": 0.02, + "learning_rate": 2.263214910214674e-05, + "loss": 3.4582, + "step": 1671680 + }, + { + "epoch": 0.02, + "learning_rate": 2.262376315463622e-05, + "loss": 3.4572, + "step": 1672192 + }, + { + "epoch": 0.02, + "learning_rate": 2.26153772071257e-05, + "loss": 3.4516, + "step": 1672704 + }, + { + "epoch": 0.02, + "learning_rate": 2.2607007638418908e-05, + "loss": 3.4581, + "step": 1673216 + }, + { + "epoch": 0.02, + "learning_rate": 2.2598621690908388e-05, + "loss": 3.4513, + "step": 1673728 + }, + { + "epoch": 0.02, + "learning_rate": 2.2590235743397868e-05, + "loss": 3.4624, + "step": 1674240 + }, + { + "epoch": 0.02, + "learning_rate": 2.2581849795887348e-05, + "loss": 3.446, + "step": 1674752 + }, + { + "epoch": 0.02, + "learning_rate": 2.257348022718056e-05, + "loss": 3.4586, + "step": 1675264 + }, + { + "epoch": 0.02, + "learning_rate": 2.256511065847377e-05, + "loss": 3.4484, + "step": 1675776 + }, + { + "epoch": 0.02, + "learning_rate": 2.255672471096325e-05, + "loss": 3.4525, + "step": 1676288 + }, + { + "epoch": 0.02, + "learning_rate": 2.254833876345273e-05, + "loss": 3.4543, + "step": 1676800 + }, + { + "epoch": 0.02, + "learning_rate": 2.2539952815942213e-05, + "loss": 3.458, + "step": 1677312 + }, + { + "epoch": 0.02, + "learning_rate": 2.2531566868431693e-05, + "loss": 3.4586, + "step": 1677824 + }, + { + "epoch": 0.02, + "learning_rate": 2.2523180920921173e-05, + "loss": 3.438, + "step": 1678336 + }, + { + "epoch": 0.02, + "learning_rate": 2.2514811352214382e-05, + "loss": 3.451, + "step": 1678848 + }, + { + "epoch": 0.03, + "eval_loss": 3.8506789207458496, + "eval_runtime": 308.6489, + "eval_samples_per_second": 1236.327, + "eval_steps_per_second": 38.636, + "step": 1679040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2506425404703862e-05, + "loss": 3.4545, + "step": 1679360 + }, + { + "epoch": 1.0, + "learning_rate": 2.2498039457193342e-05, + "loss": 3.4458, + "step": 1679872 + }, + { + "epoch": 1.0, + "learning_rate": 2.2489653509682822e-05, + "loss": 3.4533, + "step": 1680384 + }, + { + "epoch": 1.0, + "learning_rate": 2.2481267562172302e-05, + "loss": 3.457, + "step": 1680896 + }, + { + "epoch": 1.0, + "learning_rate": 2.2472881614661782e-05, + "loss": 3.4681, + "step": 1681408 + }, + { + "epoch": 1.0, + "learning_rate": 2.2464512045954994e-05, + "loss": 3.4499, + "step": 1681920 + }, + { + "epoch": 1.0, + "learning_rate": 2.2456126098444474e-05, + "loss": 3.4422, + "step": 1682432 + }, + { + "epoch": 1.0, + "learning_rate": 2.244774015093395e-05, + "loss": 3.4415, + "step": 1682944 + }, + { + "epoch": 1.0, + "learning_rate": 2.243935420342343e-05, + "loss": 3.4476, + "step": 1683456 + }, + { + "epoch": 1.0, + "learning_rate": 2.2430968255912914e-05, + "loss": 3.456, + "step": 1683968 + }, + { + "epoch": 1.0, + "learning_rate": 2.2422582308402394e-05, + "loss": 3.4512, + "step": 1684480 + }, + { + "epoch": 1.0, + "learning_rate": 2.2414196360891874e-05, + "loss": 3.4553, + "step": 1684992 + }, + { + "epoch": 1.0, + "learning_rate": 2.2405826792185083e-05, + "loss": 3.4464, + "step": 1685504 + }, + { + "epoch": 1.0, + "learning_rate": 2.2397457223478296e-05, + "loss": 3.4447, + "step": 1686016 + }, + { + "epoch": 1.0, + "learning_rate": 2.2389071275967776e-05, + "loss": 3.4428, + "step": 1686528 + }, + { + "epoch": 1.0, + "learning_rate": 2.2380685328457255e-05, + "loss": 3.4489, + "step": 1687040 + }, + { + "epoch": 1.0, + "learning_rate": 2.2372299380946735e-05, + "loss": 3.4383, + "step": 1687552 + }, + { + "epoch": 1.0, + "learning_rate": 2.2363913433436215e-05, + "loss": 3.445, + "step": 1688064 + }, + { + "epoch": 1.0, + "learning_rate": 2.2355527485925695e-05, + "loss": 3.4448, + "step": 1688576 + }, + { + "epoch": 1.0, + "learning_rate": 2.2347141538415175e-05, + "loss": 3.4633, + "step": 1689088 + }, + { + "epoch": 1.0, + "learning_rate": 2.2338755590904655e-05, + "loss": 3.4508, + "step": 1689600 + }, + { + "epoch": 1.0, + "learning_rate": 2.2330386022197868e-05, + "loss": 3.4556, + "step": 1690112 + }, + { + "epoch": 1.0, + "learning_rate": 2.2322000074687348e-05, + "loss": 3.4437, + "step": 1690624 + }, + { + "epoch": 1.0, + "learning_rate": 2.2313614127176828e-05, + "loss": 3.4561, + "step": 1691136 + }, + { + "epoch": 1.0, + "learning_rate": 2.2305228179666308e-05, + "loss": 3.4405, + "step": 1691648 + }, + { + "epoch": 1.0, + "learning_rate": 2.2296858610959517e-05, + "loss": 3.458, + "step": 1692160 + }, + { + "epoch": 1.0, + "learning_rate": 2.2288472663448997e-05, + "loss": 3.4473, + "step": 1692672 + }, + { + "epoch": 1.0, + "learning_rate": 2.2280086715938477e-05, + "loss": 3.4377, + "step": 1693184 + }, + { + "epoch": 1.0, + "learning_rate": 2.2271700768427957e-05, + "loss": 3.4377, + "step": 1693696 + }, + { + "epoch": 1.0, + "learning_rate": 2.226333119972117e-05, + "loss": 3.4408, + "step": 1694208 + }, + { + "epoch": 1.01, + "learning_rate": 2.225494525221065e-05, + "loss": 3.448, + "step": 1694720 + }, + { + "epoch": 1.01, + "learning_rate": 2.224655930470013e-05, + "loss": 3.4474, + "step": 1695232 + }, + { + "epoch": 1.01, + "learning_rate": 2.2238173357189606e-05, + "loss": 3.4557, + "step": 1695744 + }, + { + "epoch": 1.01, + "learning_rate": 2.222980378848282e-05, + "loss": 3.4568, + "step": 1696256 + }, + { + "epoch": 1.01, + "learning_rate": 2.22214178409723e-05, + "loss": 3.4403, + "step": 1696768 + }, + { + "epoch": 1.01, + "learning_rate": 2.221303189346178e-05, + "loss": 3.4558, + "step": 1697280 + }, + { + "epoch": 1.01, + "learning_rate": 2.220466232475499e-05, + "loss": 3.4498, + "step": 1697792 + }, + { + "epoch": 1.01, + "learning_rate": 2.219627637724447e-05, + "loss": 3.4401, + "step": 1698304 + }, + { + "epoch": 1.01, + "learning_rate": 2.218789042973395e-05, + "loss": 3.4321, + "step": 1698816 + }, + { + "epoch": 1.01, + "learning_rate": 2.217950448222343e-05, + "loss": 3.4442, + "step": 1699328 + }, + { + "epoch": 1.01, + "learning_rate": 2.2171134913516643e-05, + "loss": 3.4492, + "step": 1699840 + }, + { + "epoch": 1.01, + "learning_rate": 2.2162748966006123e-05, + "loss": 3.4513, + "step": 1700352 + }, + { + "epoch": 1.01, + "learning_rate": 2.2154363018495603e-05, + "loss": 3.445, + "step": 1700864 + }, + { + "epoch": 1.01, + "learning_rate": 2.214597707098508e-05, + "loss": 3.4402, + "step": 1701376 + }, + { + "epoch": 1.01, + "learning_rate": 2.213759112347456e-05, + "loss": 3.4584, + "step": 1701888 + }, + { + "epoch": 1.01, + "learning_rate": 2.212920517596404e-05, + "loss": 3.4443, + "step": 1702400 + }, + { + "epoch": 1.01, + "learning_rate": 2.2120819228453523e-05, + "loss": 3.441, + "step": 1702912 + }, + { + "epoch": 1.01, + "learning_rate": 2.2112433280943002e-05, + "loss": 3.4314, + "step": 1703424 + }, + { + "epoch": 1.01, + "learning_rate": 2.210406371223621e-05, + "loss": 3.4311, + "step": 1703936 + }, + { + "epoch": 1.01, + "learning_rate": 2.209567776472569e-05, + "loss": 3.4512, + "step": 1704448 + }, + { + "epoch": 1.01, + "learning_rate": 2.208729181721517e-05, + "loss": 3.4468, + "step": 1704960 + }, + { + "epoch": 1.01, + "learning_rate": 2.207890586970465e-05, + "loss": 3.4415, + "step": 1705472 + }, + { + "epoch": 1.01, + "learning_rate": 2.207051992219413e-05, + "loss": 3.4371, + "step": 1705984 + }, + { + "epoch": 1.01, + "learning_rate": 2.2062150353487344e-05, + "loss": 3.4477, + "step": 1706496 + }, + { + "epoch": 1.01, + "learning_rate": 2.2053764405976824e-05, + "loss": 3.4245, + "step": 1707008 + }, + { + "epoch": 1.01, + "learning_rate": 2.2045378458466304e-05, + "loss": 3.4515, + "step": 1707520 + }, + { + "epoch": 1.01, + "learning_rate": 2.2036992510955784e-05, + "loss": 3.4384, + "step": 1708032 + }, + { + "epoch": 1.01, + "learning_rate": 2.202860656344526e-05, + "loss": 3.4414, + "step": 1708544 + }, + { + "epoch": 1.01, + "learning_rate": 2.202022061593474e-05, + "loss": 3.4453, + "step": 1709056 + }, + { + "epoch": 1.01, + "learning_rate": 2.2011851047227956e-05, + "loss": 3.4413, + "step": 1709568 + }, + { + "epoch": 1.01, + "learning_rate": 2.2003465099717436e-05, + "loss": 3.4346, + "step": 1710080 + }, + { + "epoch": 1.01, + "learning_rate": 2.1995079152206913e-05, + "loss": 3.4509, + "step": 1710592 + }, + { + "epoch": 1.01, + "learning_rate": 2.1986693204696393e-05, + "loss": 3.4354, + "step": 1711104 + }, + { + "epoch": 1.01, + "learning_rate": 2.1978307257185873e-05, + "loss": 3.4411, + "step": 1711616 + }, + { + "epoch": 1.01, + "learning_rate": 2.1969921309675353e-05, + "loss": 3.4476, + "step": 1712128 + }, + { + "epoch": 1.01, + "learning_rate": 2.1961551740968565e-05, + "loss": 3.4475, + "step": 1712640 + }, + { + "epoch": 1.01, + "learning_rate": 2.1953165793458045e-05, + "loss": 3.4336, + "step": 1713152 + }, + { + "epoch": 1.01, + "learning_rate": 2.1944779845947525e-05, + "loss": 3.4392, + "step": 1713664 + }, + { + "epoch": 1.01, + "learning_rate": 2.1936393898437005e-05, + "loss": 3.4323, + "step": 1714176 + }, + { + "epoch": 1.01, + "learning_rate": 2.1928024329730214e-05, + "loss": 3.4319, + "step": 1714688 + }, + { + "epoch": 1.01, + "learning_rate": 2.1919638382219694e-05, + "loss": 3.448, + "step": 1715200 + }, + { + "epoch": 1.01, + "learning_rate": 2.1911252434709177e-05, + "loss": 3.4431, + "step": 1715712 + }, + { + "epoch": 1.01, + "learning_rate": 2.1902866487198657e-05, + "loss": 3.4535, + "step": 1716224 + }, + { + "epoch": 1.01, + "learning_rate": 2.1894480539688137e-05, + "loss": 3.4448, + "step": 1716736 + }, + { + "epoch": 1.01, + "learning_rate": 2.1886094592177617e-05, + "loss": 3.4605, + "step": 1717248 + }, + { + "epoch": 1.01, + "learning_rate": 2.1877708644667094e-05, + "loss": 3.4361, + "step": 1717760 + }, + { + "epoch": 1.01, + "learning_rate": 2.1869322697156574e-05, + "loss": 3.4456, + "step": 1718272 + }, + { + "epoch": 1.01, + "learning_rate": 2.1860953128449786e-05, + "loss": 3.4523, + "step": 1718784 + }, + { + "epoch": 1.01, + "learning_rate": 2.1852567180939266e-05, + "loss": 3.437, + "step": 1719296 + }, + { + "epoch": 1.01, + "learning_rate": 2.1844181233428746e-05, + "loss": 3.4462, + "step": 1719808 + }, + { + "epoch": 1.01, + "learning_rate": 2.1835795285918226e-05, + "loss": 3.4487, + "step": 1720320 + }, + { + "epoch": 1.01, + "learning_rate": 2.1827409338407706e-05, + "loss": 3.4554, + "step": 1720832 + }, + { + "epoch": 1.01, + "learning_rate": 2.1819039769700915e-05, + "loss": 3.4434, + "step": 1721344 + }, + { + "epoch": 1.01, + "learning_rate": 2.1810653822190395e-05, + "loss": 3.4339, + "step": 1721856 + }, + { + "epoch": 1.01, + "learning_rate": 2.180226787467988e-05, + "loss": 3.4353, + "step": 1722368 + }, + { + "epoch": 1.01, + "learning_rate": 2.179388192716936e-05, + "loss": 3.442, + "step": 1722880 + }, + { + "epoch": 1.01, + "learning_rate": 2.1785512358462567e-05, + "loss": 3.4501, + "step": 1723392 + }, + { + "epoch": 1.01, + "learning_rate": 2.1777126410952047e-05, + "loss": 3.4472, + "step": 1723904 + }, + { + "epoch": 1.01, + "learning_rate": 2.1768740463441527e-05, + "loss": 3.4452, + "step": 1724416 + }, + { + "epoch": 1.02, + "learning_rate": 2.1760354515931007e-05, + "loss": 3.434, + "step": 1724928 + }, + { + "epoch": 1.02, + "learning_rate": 2.1751968568420487e-05, + "loss": 3.4365, + "step": 1725440 + }, + { + "epoch": 1.02, + "learning_rate": 2.174358262090997e-05, + "loss": 3.436, + "step": 1725952 + }, + { + "epoch": 1.02, + "learning_rate": 2.1735196673399447e-05, + "loss": 3.4394, + "step": 1726464 + }, + { + "epoch": 1.02, + "learning_rate": 2.172682710469266e-05, + "loss": 3.4533, + "step": 1726976 + }, + { + "epoch": 1.02, + "learning_rate": 2.171844115718214e-05, + "loss": 3.4604, + "step": 1727488 + }, + { + "epoch": 1.02, + "learning_rate": 2.171005520967162e-05, + "loss": 3.4506, + "step": 1728000 + }, + { + "epoch": 1.02, + "learning_rate": 2.17016692621611e-05, + "loss": 3.4337, + "step": 1728512 + }, + { + "epoch": 1.02, + "learning_rate": 2.169328331465058e-05, + "loss": 3.4464, + "step": 1729024 + }, + { + "epoch": 1.02, + "learning_rate": 2.168489736714006e-05, + "loss": 3.4381, + "step": 1729536 + }, + { + "epoch": 1.02, + "learning_rate": 2.167651141962954e-05, + "loss": 3.4503, + "step": 1730048 + }, + { + "epoch": 1.02, + "learning_rate": 2.166812547211902e-05, + "loss": 3.441, + "step": 1730560 + }, + { + "epoch": 1.02, + "learning_rate": 2.165975590341223e-05, + "loss": 3.4496, + "step": 1731072 + }, + { + "epoch": 1.02, + "learning_rate": 2.165136995590171e-05, + "loss": 3.4422, + "step": 1731584 + }, + { + "epoch": 1.02, + "learning_rate": 2.164298400839119e-05, + "loss": 3.4403, + "step": 1732096 + }, + { + "epoch": 1.02, + "learning_rate": 2.163459806088067e-05, + "loss": 3.4389, + "step": 1732608 + }, + { + "epoch": 1.02, + "learning_rate": 2.162622849217388e-05, + "loss": 3.4378, + "step": 1733120 + }, + { + "epoch": 1.02, + "learning_rate": 2.161784254466336e-05, + "loss": 3.4317, + "step": 1733632 + }, + { + "epoch": 1.02, + "learning_rate": 2.160945659715284e-05, + "loss": 3.4525, + "step": 1734144 + }, + { + "epoch": 1.02, + "learning_rate": 2.160107064964232e-05, + "loss": 3.4378, + "step": 1734656 + }, + { + "epoch": 1.02, + "learning_rate": 2.1592701080935533e-05, + "loss": 3.4382, + "step": 1735168 + }, + { + "epoch": 1.02, + "learning_rate": 2.1584315133425013e-05, + "loss": 3.4356, + "step": 1735680 + }, + { + "epoch": 1.02, + "learning_rate": 2.1575929185914493e-05, + "loss": 3.4412, + "step": 1736192 + }, + { + "epoch": 1.02, + "learning_rate": 2.1567559617207702e-05, + "loss": 3.4459, + "step": 1736704 + }, + { + "epoch": 1.02, + "learning_rate": 2.1559173669697182e-05, + "loss": 3.4407, + "step": 1737216 + }, + { + "epoch": 1.02, + "learning_rate": 2.1550787722186662e-05, + "loss": 3.4554, + "step": 1737728 + }, + { + "epoch": 1.02, + "learning_rate": 2.1542401774676142e-05, + "loss": 3.4514, + "step": 1738240 + }, + { + "epoch": 1.02, + "learning_rate": 2.1534015827165625e-05, + "loss": 3.4458, + "step": 1738752 + }, + { + "epoch": 1.02, + "learning_rate": 2.1525629879655102e-05, + "loss": 3.4445, + "step": 1739264 + }, + { + "epoch": 1.02, + "learning_rate": 2.1517260310948314e-05, + "loss": 3.4324, + "step": 1739776 + }, + { + "epoch": 1.02, + "learning_rate": 2.1508874363437794e-05, + "loss": 3.4537, + "step": 1740288 + }, + { + "epoch": 1.02, + "learning_rate": 2.1500488415927274e-05, + "loss": 3.4375, + "step": 1740800 + }, + { + "epoch": 1.02, + "learning_rate": 2.1492102468416754e-05, + "loss": 3.4396, + "step": 1741312 + }, + { + "epoch": 1.02, + "learning_rate": 2.1483716520906234e-05, + "loss": 3.4353, + "step": 1741824 + }, + { + "epoch": 1.02, + "learning_rate": 2.1475330573395714e-05, + "loss": 3.444, + "step": 1742336 + }, + { + "epoch": 1.02, + "learning_rate": 2.1466944625885194e-05, + "loss": 3.4327, + "step": 1742848 + }, + { + "epoch": 1.02, + "learning_rate": 2.1458558678374674e-05, + "loss": 3.4414, + "step": 1743360 + }, + { + "epoch": 1.02, + "learning_rate": 2.1450189109667883e-05, + "loss": 3.4376, + "step": 1743872 + }, + { + "epoch": 1.02, + "learning_rate": 2.1441803162157363e-05, + "loss": 3.4423, + "step": 1744384 + }, + { + "epoch": 1.02, + "learning_rate": 2.1433417214646846e-05, + "loss": 3.4348, + "step": 1744896 + }, + { + "epoch": 1.02, + "learning_rate": 2.1425031267136326e-05, + "loss": 3.4511, + "step": 1745408 + }, + { + "epoch": 1.02, + "learning_rate": 2.1416661698429536e-05, + "loss": 3.4465, + "step": 1745920 + }, + { + "epoch": 1.02, + "learning_rate": 2.1408275750919015e-05, + "loss": 3.4528, + "step": 1746432 + }, + { + "epoch": 1.02, + "learning_rate": 2.1399889803408495e-05, + "loss": 3.4309, + "step": 1746944 + }, + { + "epoch": 1.02, + "learning_rate": 2.1391503855897975e-05, + "loss": 3.4458, + "step": 1747456 + }, + { + "epoch": 1.02, + "learning_rate": 2.1383117908387455e-05, + "loss": 3.4446, + "step": 1747968 + }, + { + "epoch": 1.02, + "learning_rate": 2.1374731960876935e-05, + "loss": 3.4451, + "step": 1748480 + }, + { + "epoch": 1.02, + "learning_rate": 2.1366346013366415e-05, + "loss": 3.4426, + "step": 1748992 + }, + { + "epoch": 1.02, + "learning_rate": 2.1357976444659628e-05, + "loss": 3.4453, + "step": 1749504 + }, + { + "epoch": 1.02, + "learning_rate": 2.1349590497149104e-05, + "loss": 3.4363, + "step": 1750016 + }, + { + "epoch": 1.02, + "learning_rate": 2.1341204549638584e-05, + "loss": 3.4558, + "step": 1750528 + }, + { + "epoch": 1.02, + "learning_rate": 2.1332818602128064e-05, + "loss": 3.4296, + "step": 1751040 + }, + { + "epoch": 1.02, + "learning_rate": 2.132444903342128e-05, + "loss": 3.4466, + "step": 1751552 + }, + { + "epoch": 1.02, + "learning_rate": 2.131607946471449e-05, + "loss": 3.4392, + "step": 1752064 + }, + { + "epoch": 1.02, + "learning_rate": 2.130769351720397e-05, + "loss": 3.4409, + "step": 1752576 + }, + { + "epoch": 1.02, + "learning_rate": 2.129930756969345e-05, + "loss": 3.4414, + "step": 1753088 + }, + { + "epoch": 1.02, + "learning_rate": 2.129092162218293e-05, + "loss": 3.4441, + "step": 1753600 + }, + { + "epoch": 1.02, + "learning_rate": 2.128253567467241e-05, + "loss": 3.4482, + "step": 1754112 + }, + { + "epoch": 1.02, + "learning_rate": 2.127414972716189e-05, + "loss": 3.426, + "step": 1754624 + }, + { + "epoch": 1.02, + "learning_rate": 2.12657801584551e-05, + "loss": 3.4443, + "step": 1755136 + }, + { + "epoch": 1.03, + "eval_loss": 3.8522608280181885, + "eval_runtime": 307.0438, + "eval_samples_per_second": 1242.79, + "eval_steps_per_second": 38.838, + "step": 1755360 + }, + { + "epoch": 0.0, + "learning_rate": 2.1257394210944578e-05, + "loss": 3.4399, + "step": 1755648 + }, + { + "epoch": 0.0, + "learning_rate": 2.1249008263434058e-05, + "loss": 3.4329, + "step": 1756160 + }, + { + "epoch": 0.0, + "learning_rate": 2.1240622315923538e-05, + "loss": 3.442, + "step": 1756672 + }, + { + "epoch": 0.0, + "learning_rate": 2.1232236368413018e-05, + "loss": 3.4428, + "step": 1757184 + }, + { + "epoch": 0.0, + "learning_rate": 2.122386679970623e-05, + "loss": 3.4547, + "step": 1757696 + }, + { + "epoch": 0.0, + "learning_rate": 2.1215497230999443e-05, + "loss": 3.443, + "step": 1758208 + }, + { + "epoch": 0.0, + "learning_rate": 2.1207111283488923e-05, + "loss": 3.4318, + "step": 1758720 + }, + { + "epoch": 0.0, + "learning_rate": 2.1198725335978403e-05, + "loss": 3.4311, + "step": 1759232 + }, + { + "epoch": 0.0, + "learning_rate": 2.119033938846788e-05, + "loss": 3.439, + "step": 1759744 + }, + { + "epoch": 0.0, + "learning_rate": 2.1181953440957363e-05, + "loss": 3.4431, + "step": 1760256 + }, + { + "epoch": 0.0, + "learning_rate": 2.1173567493446843e-05, + "loss": 3.4395, + "step": 1760768 + }, + { + "epoch": 0.0, + "learning_rate": 2.1165181545936323e-05, + "loss": 3.4425, + "step": 1761280 + }, + { + "epoch": 0.0, + "learning_rate": 2.1156811977229532e-05, + "loss": 3.4379, + "step": 1761792 + }, + { + "epoch": 0.0, + "learning_rate": 2.114842602971901e-05, + "loss": 3.4375, + "step": 1762304 + }, + { + "epoch": 0.0, + "learning_rate": 2.114004008220849e-05, + "loss": 3.4285, + "step": 1762816 + }, + { + "epoch": 0.0, + "learning_rate": 2.1131670513501704e-05, + "loss": 3.4346, + "step": 1763328 + }, + { + "epoch": 0.0, + "learning_rate": 2.1123284565991184e-05, + "loss": 3.4317, + "step": 1763840 + }, + { + "epoch": 0.0, + "learning_rate": 2.1114898618480664e-05, + "loss": 3.4346, + "step": 1764352 + }, + { + "epoch": 0.0, + "learning_rate": 2.1106512670970144e-05, + "loss": 3.4346, + "step": 1764864 + }, + { + "epoch": 0.0, + "learning_rate": 2.1098126723459624e-05, + "loss": 3.4481, + "step": 1765376 + }, + { + "epoch": 0.0, + "learning_rate": 2.1089740775949104e-05, + "loss": 3.4417, + "step": 1765888 + }, + { + "epoch": 0.0, + "learning_rate": 2.1081354828438584e-05, + "loss": 3.4442, + "step": 1766400 + }, + { + "epoch": 0.0, + "learning_rate": 2.1072968880928064e-05, + "loss": 3.4333, + "step": 1766912 + }, + { + "epoch": 0.0, + "learning_rate": 2.1064599312221276e-05, + "loss": 3.4433, + "step": 1767424 + }, + { + "epoch": 0.0, + "learning_rate": 2.1056229743514485e-05, + "loss": 3.4295, + "step": 1767936 + }, + { + "epoch": 0.0, + "learning_rate": 2.1047843796003965e-05, + "loss": 3.4484, + "step": 1768448 + }, + { + "epoch": 0.0, + "learning_rate": 2.1039457848493445e-05, + "loss": 3.4314, + "step": 1768960 + }, + { + "epoch": 0.0, + "learning_rate": 2.1031071900982925e-05, + "loss": 3.4287, + "step": 1769472 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022685953472405e-05, + "loss": 3.4282, + "step": 1769984 + }, + { + "epoch": 0.0, + "learning_rate": 2.1014300005961885e-05, + "loss": 3.4325, + "step": 1770496 + }, + { + "epoch": 0.01, + "learning_rate": 2.1005914058451365e-05, + "loss": 3.4337, + "step": 1771008 + }, + { + "epoch": 0.01, + "learning_rate": 2.0997528110940845e-05, + "loss": 3.4395, + "step": 1771520 + }, + { + "epoch": 0.01, + "learning_rate": 2.0989158542234058e-05, + "loss": 3.4444, + "step": 1772032 + }, + { + "epoch": 0.01, + "learning_rate": 2.0980772594723534e-05, + "loss": 3.442, + "step": 1772544 + }, + { + "epoch": 0.01, + "learning_rate": 2.0972386647213017e-05, + "loss": 3.4336, + "step": 1773056 + }, + { + "epoch": 0.01, + "learning_rate": 2.0964000699702497e-05, + "loss": 3.4443, + "step": 1773568 + }, + { + "epoch": 0.01, + "learning_rate": 2.095564750979944e-05, + "loss": 3.4426, + "step": 1774080 + }, + { + "epoch": 0.01, + "learning_rate": 2.094726156228892e-05, + "loss": 3.4256, + "step": 1774592 + }, + { + "epoch": 0.01, + "learning_rate": 2.09388756147784e-05, + "loss": 3.4256, + "step": 1775104 + }, + { + "epoch": 0.01, + "learning_rate": 2.093048966726788e-05, + "loss": 3.4309, + "step": 1775616 + }, + { + "epoch": 0.01, + "learning_rate": 2.092210371975736e-05, + "loss": 3.437, + "step": 1776128 + }, + { + "epoch": 0.01, + "learning_rate": 2.091373415105057e-05, + "loss": 3.4404, + "step": 1776640 + }, + { + "epoch": 0.01, + "learning_rate": 2.090534820354005e-05, + "loss": 3.4345, + "step": 1777152 + }, + { + "epoch": 0.01, + "learning_rate": 2.089696225602953e-05, + "loss": 3.429, + "step": 1777664 + }, + { + "epoch": 0.01, + "learning_rate": 2.0888576308519008e-05, + "loss": 3.4455, + "step": 1778176 + }, + { + "epoch": 0.01, + "learning_rate": 2.0880190361008488e-05, + "loss": 3.438, + "step": 1778688 + }, + { + "epoch": 0.01, + "learning_rate": 2.087180441349797e-05, + "loss": 3.4323, + "step": 1779200 + }, + { + "epoch": 0.01, + "learning_rate": 2.086341846598745e-05, + "loss": 3.4211, + "step": 1779712 + }, + { + "epoch": 0.01, + "learning_rate": 2.085504889728066e-05, + "loss": 3.4165, + "step": 1780224 + }, + { + "epoch": 0.01, + "learning_rate": 2.084666294977014e-05, + "loss": 3.4448, + "step": 1780736 + }, + { + "epoch": 0.01, + "learning_rate": 2.083827700225962e-05, + "loss": 3.4312, + "step": 1781248 + }, + { + "epoch": 0.01, + "learning_rate": 2.08298910547491e-05, + "loss": 3.4356, + "step": 1781760 + }, + { + "epoch": 0.01, + "learning_rate": 2.082150510723858e-05, + "loss": 3.4295, + "step": 1782272 + }, + { + "epoch": 0.01, + "learning_rate": 2.0813135538531792e-05, + "loss": 3.4313, + "step": 1782784 + }, + { + "epoch": 0.01, + "learning_rate": 2.0804749591021272e-05, + "loss": 3.4137, + "step": 1783296 + }, + { + "epoch": 0.01, + "learning_rate": 2.0796363643510752e-05, + "loss": 3.4353, + "step": 1783808 + }, + { + "epoch": 0.01, + "learning_rate": 2.0787977696000232e-05, + "loss": 3.4288, + "step": 1784320 + }, + { + "epoch": 0.01, + "learning_rate": 2.077959174848971e-05, + "loss": 3.4301, + "step": 1784832 + }, + { + "epoch": 0.01, + "learning_rate": 2.077120580097919e-05, + "loss": 3.4363, + "step": 1785344 + }, + { + "epoch": 0.01, + "learning_rate": 2.0762836232272405e-05, + "loss": 3.429, + "step": 1785856 + }, + { + "epoch": 0.01, + "learning_rate": 2.0754450284761885e-05, + "loss": 3.4236, + "step": 1786368 + }, + { + "epoch": 0.01, + "learning_rate": 2.074606433725136e-05, + "loss": 3.4393, + "step": 1786880 + }, + { + "epoch": 0.01, + "learning_rate": 2.073767838974084e-05, + "loss": 3.4241, + "step": 1787392 + }, + { + "epoch": 0.01, + "learning_rate": 2.072929244223032e-05, + "loss": 3.4244, + "step": 1787904 + }, + { + "epoch": 0.01, + "learning_rate": 2.07209064947198e-05, + "loss": 3.4408, + "step": 1788416 + }, + { + "epoch": 0.01, + "learning_rate": 2.0712536926013014e-05, + "loss": 3.4347, + "step": 1788928 + }, + { + "epoch": 0.01, + "learning_rate": 2.0704150978502494e-05, + "loss": 3.4187, + "step": 1789440 + }, + { + "epoch": 0.01, + "learning_rate": 2.0695765030991974e-05, + "loss": 3.4322, + "step": 1789952 + }, + { + "epoch": 0.01, + "learning_rate": 2.0687379083481453e-05, + "loss": 3.4205, + "step": 1790464 + }, + { + "epoch": 0.01, + "learning_rate": 2.0679009514774663e-05, + "loss": 3.4204, + "step": 1790976 + }, + { + "epoch": 0.01, + "learning_rate": 2.0670623567264143e-05, + "loss": 3.4387, + "step": 1791488 + }, + { + "epoch": 0.01, + "learning_rate": 2.0662237619753626e-05, + "loss": 3.4336, + "step": 1792000 + }, + { + "epoch": 0.01, + "learning_rate": 2.0653851672243106e-05, + "loss": 3.4389, + "step": 1792512 + }, + { + "epoch": 0.01, + "learning_rate": 2.0645465724732586e-05, + "loss": 3.4338, + "step": 1793024 + }, + { + "epoch": 0.01, + "learning_rate": 2.0637079777222066e-05, + "loss": 3.45, + "step": 1793536 + }, + { + "epoch": 0.01, + "learning_rate": 2.0628693829711542e-05, + "loss": 3.4272, + "step": 1794048 + }, + { + "epoch": 0.01, + "learning_rate": 2.0620307882201022e-05, + "loss": 3.4368, + "step": 1794560 + }, + { + "epoch": 0.01, + "learning_rate": 2.0611938313494235e-05, + "loss": 3.443, + "step": 1795072 + }, + { + "epoch": 0.01, + "learning_rate": 2.0603552365983718e-05, + "loss": 3.4263, + "step": 1795584 + }, + { + "epoch": 0.01, + "learning_rate": 2.0595166418473195e-05, + "loss": 3.4337, + "step": 1796096 + }, + { + "epoch": 0.01, + "learning_rate": 2.0586780470962675e-05, + "loss": 3.4405, + "step": 1796608 + }, + { + "epoch": 0.01, + "learning_rate": 2.0578394523452155e-05, + "loss": 3.4425, + "step": 1797120 + }, + { + "epoch": 0.01, + "learning_rate": 2.0570024954745364e-05, + "loss": 3.4358, + "step": 1797632 + }, + { + "epoch": 0.01, + "learning_rate": 2.0561639007234844e-05, + "loss": 3.4227, + "step": 1798144 + }, + { + "epoch": 0.01, + "learning_rate": 2.0553253059724327e-05, + "loss": 3.4179, + "step": 1798656 + }, + { + "epoch": 0.01, + "learning_rate": 2.0544867112213807e-05, + "loss": 3.4313, + "step": 1799168 + }, + { + "epoch": 0.01, + "learning_rate": 2.0536481164703287e-05, + "loss": 3.4422, + "step": 1799680 + }, + { + "epoch": 0.01, + "learning_rate": 2.0528095217192767e-05, + "loss": 3.4359, + "step": 1800192 + }, + { + "epoch": 0.01, + "learning_rate": 2.0519709269682247e-05, + "loss": 3.433, + "step": 1800704 + }, + { + "epoch": 0.02, + "learning_rate": 2.0511323322171723e-05, + "loss": 3.4203, + "step": 1801216 + }, + { + "epoch": 0.02, + "learning_rate": 2.0502953753464936e-05, + "loss": 3.4299, + "step": 1801728 + }, + { + "epoch": 0.02, + "learning_rate": 2.049456780595442e-05, + "loss": 3.4278, + "step": 1802240 + }, + { + "epoch": 0.02, + "learning_rate": 2.04861818584439e-05, + "loss": 3.4312, + "step": 1802752 + }, + { + "epoch": 0.02, + "learning_rate": 2.0477795910933376e-05, + "loss": 3.4382, + "step": 1803264 + }, + { + "epoch": 0.02, + "learning_rate": 2.0469426342226588e-05, + "loss": 3.451, + "step": 1803776 + }, + { + "epoch": 0.02, + "learning_rate": 2.0461040394716068e-05, + "loss": 3.4377, + "step": 1804288 + }, + { + "epoch": 0.02, + "learning_rate": 2.0452654447205548e-05, + "loss": 3.4258, + "step": 1804800 + }, + { + "epoch": 0.02, + "learning_rate": 2.0444268499695028e-05, + "loss": 3.4353, + "step": 1805312 + }, + { + "epoch": 0.02, + "learning_rate": 2.0435882552184508e-05, + "loss": 3.429, + "step": 1805824 + }, + { + "epoch": 0.02, + "learning_rate": 2.042751298347772e-05, + "loss": 3.4401, + "step": 1806336 + }, + { + "epoch": 0.02, + "learning_rate": 2.0419127035967197e-05, + "loss": 3.4315, + "step": 1806848 + }, + { + "epoch": 0.02, + "learning_rate": 2.0410741088456677e-05, + "loss": 3.4411, + "step": 1807360 + }, + { + "epoch": 0.02, + "learning_rate": 2.0402355140946157e-05, + "loss": 3.4326, + "step": 1807872 + }, + { + "epoch": 0.02, + "learning_rate": 2.0393969193435637e-05, + "loss": 3.4215, + "step": 1808384 + }, + { + "epoch": 0.02, + "learning_rate": 2.038558324592512e-05, + "loss": 3.4339, + "step": 1808896 + }, + { + "epoch": 0.02, + "learning_rate": 2.03771972984146e-05, + "loss": 3.4254, + "step": 1809408 + }, + { + "epoch": 0.02, + "learning_rate": 2.036881135090408e-05, + "loss": 3.4246, + "step": 1809920 + }, + { + "epoch": 0.02, + "learning_rate": 2.036044178219729e-05, + "loss": 3.4364, + "step": 1810432 + }, + { + "epoch": 0.02, + "learning_rate": 2.035205583468677e-05, + "loss": 3.4309, + "step": 1810944 + }, + { + "epoch": 0.02, + "learning_rate": 2.034366988717625e-05, + "loss": 3.4243, + "step": 1811456 + }, + { + "epoch": 0.02, + "learning_rate": 2.033528393966573e-05, + "loss": 3.4288, + "step": 1811968 + }, + { + "epoch": 0.02, + "learning_rate": 2.032691437095894e-05, + "loss": 3.4238, + "step": 1812480 + }, + { + "epoch": 0.02, + "learning_rate": 2.031854480225215e-05, + "loss": 3.4368, + "step": 1812992 + }, + { + "epoch": 0.02, + "learning_rate": 2.031015885474163e-05, + "loss": 3.4271, + "step": 1813504 + }, + { + "epoch": 0.02, + "learning_rate": 2.030177290723111e-05, + "loss": 3.4454, + "step": 1814016 + }, + { + "epoch": 0.02, + "learning_rate": 2.029338695972059e-05, + "loss": 3.4417, + "step": 1814528 + }, + { + "epoch": 0.02, + "learning_rate": 2.0285001012210074e-05, + "loss": 3.4388, + "step": 1815040 + }, + { + "epoch": 0.02, + "learning_rate": 2.0276615064699554e-05, + "loss": 3.4324, + "step": 1815552 + }, + { + "epoch": 0.02, + "learning_rate": 2.0268245495992763e-05, + "loss": 3.4201, + "step": 1816064 + }, + { + "epoch": 0.02, + "learning_rate": 2.0259859548482243e-05, + "loss": 3.4356, + "step": 1816576 + }, + { + "epoch": 0.02, + "learning_rate": 2.0251473600971723e-05, + "loss": 3.4323, + "step": 1817088 + }, + { + "epoch": 0.02, + "learning_rate": 2.0243087653461203e-05, + "loss": 3.4248, + "step": 1817600 + }, + { + "epoch": 0.02, + "learning_rate": 2.0234701705950683e-05, + "loss": 3.4254, + "step": 1818112 + }, + { + "epoch": 0.02, + "learning_rate": 2.0226315758440163e-05, + "loss": 3.4349, + "step": 1818624 + }, + { + "epoch": 0.02, + "learning_rate": 2.0217929810929643e-05, + "loss": 3.4213, + "step": 1819136 + }, + { + "epoch": 0.02, + "learning_rate": 2.0209543863419123e-05, + "loss": 3.4326, + "step": 1819648 + }, + { + "epoch": 0.02, + "learning_rate": 2.0201174294712332e-05, + "loss": 3.4241, + "step": 1820160 + }, + { + "epoch": 0.02, + "learning_rate": 2.0192788347201812e-05, + "loss": 3.4346, + "step": 1820672 + }, + { + "epoch": 0.02, + "learning_rate": 2.0184402399691295e-05, + "loss": 3.4189, + "step": 1821184 + }, + { + "epoch": 0.02, + "learning_rate": 2.0176016452180775e-05, + "loss": 3.4429, + "step": 1821696 + }, + { + "epoch": 0.02, + "learning_rate": 2.0167646883473984e-05, + "loss": 3.4348, + "step": 1822208 + }, + { + "epoch": 0.02, + "learning_rate": 2.0159260935963464e-05, + "loss": 3.4434, + "step": 1822720 + }, + { + "epoch": 0.02, + "learning_rate": 2.0150874988452944e-05, + "loss": 3.4193, + "step": 1823232 + }, + { + "epoch": 0.02, + "learning_rate": 2.0142489040942424e-05, + "loss": 3.4355, + "step": 1823744 + }, + { + "epoch": 0.02, + "learning_rate": 2.0134103093431904e-05, + "loss": 3.4312, + "step": 1824256 + }, + { + "epoch": 0.02, + "learning_rate": 2.0125717145921384e-05, + "loss": 3.4368, + "step": 1824768 + }, + { + "epoch": 0.02, + "learning_rate": 2.0117331198410864e-05, + "loss": 3.4305, + "step": 1825280 + }, + { + "epoch": 0.02, + "learning_rate": 2.0108945250900344e-05, + "loss": 3.4321, + "step": 1825792 + }, + { + "epoch": 0.02, + "learning_rate": 2.0100575682193556e-05, + "loss": 3.4312, + "step": 1826304 + }, + { + "epoch": 0.02, + "learning_rate": 2.0092189734683033e-05, + "loss": 3.4425, + "step": 1826816 + }, + { + "epoch": 0.02, + "learning_rate": 2.0083803787172513e-05, + "loss": 3.4204, + "step": 1827328 + }, + { + "epoch": 0.02, + "learning_rate": 2.007543421846573e-05, + "loss": 3.4352, + "step": 1827840 + }, + { + "epoch": 0.02, + "learning_rate": 2.0067064649758938e-05, + "loss": 3.4304, + "step": 1828352 + }, + { + "epoch": 0.02, + "learning_rate": 2.0058678702248418e-05, + "loss": 3.429, + "step": 1828864 + }, + { + "epoch": 0.02, + "learning_rate": 2.0050292754737898e-05, + "loss": 3.4315, + "step": 1829376 + }, + { + "epoch": 0.02, + "learning_rate": 2.0041906807227378e-05, + "loss": 3.4328, + "step": 1829888 + }, + { + "epoch": 0.02, + "learning_rate": 2.0033520859716858e-05, + "loss": 3.441, + "step": 1830400 + }, + { + "epoch": 0.02, + "learning_rate": 2.0025134912206338e-05, + "loss": 3.4136, + "step": 1830912 + }, + { + "epoch": 0.02, + "learning_rate": 2.001676534349955e-05, + "loss": 3.4359, + "step": 1831424 + }, + { + "epoch": 0.03, + "eval_loss": 3.85353684425354, + "eval_runtime": 305.4976, + "eval_samples_per_second": 1249.08, + "eval_steps_per_second": 39.035, + "step": 1831680 + }, + { + "epoch": 1.0, + "learning_rate": 2.000837939598903e-05, + "loss": 3.4276, + "step": 1831936 + }, + { + "epoch": 1.0, + "learning_rate": 1.9999993448478507e-05, + "loss": 3.4237, + "step": 1832448 + }, + { + "epoch": 1.0, + "learning_rate": 1.9991607500967987e-05, + "loss": 3.4296, + "step": 1832960 + }, + { + "epoch": 1.0, + "learning_rate": 1.9983221553457467e-05, + "loss": 3.4306, + "step": 1833472 + }, + { + "epoch": 1.0, + "learning_rate": 1.997483560594695e-05, + "loss": 3.4463, + "step": 1833984 + }, + { + "epoch": 1.0, + "learning_rate": 1.996646603724016e-05, + "loss": 3.4286, + "step": 1834496 + }, + { + "epoch": 1.0, + "learning_rate": 1.995808008972964e-05, + "loss": 3.4278, + "step": 1835008 + }, + { + "epoch": 1.0, + "learning_rate": 1.994969414221912e-05, + "loss": 3.4221, + "step": 1835520 + }, + { + "epoch": 1.0, + "learning_rate": 1.99413081947086e-05, + "loss": 3.4246, + "step": 1836032 + }, + { + "epoch": 1.0, + "learning_rate": 1.993292224719808e-05, + "loss": 3.4339, + "step": 1836544 + }, + { + "epoch": 1.0, + "learning_rate": 1.992453629968756e-05, + "loss": 3.4252, + "step": 1837056 + }, + { + "epoch": 1.0, + "learning_rate": 1.991615035217704e-05, + "loss": 3.4343, + "step": 1837568 + }, + { + "epoch": 1.0, + "learning_rate": 1.990778078347025e-05, + "loss": 3.4252, + "step": 1838080 + }, + { + "epoch": 1.0, + "learning_rate": 1.989941121476346e-05, + "loss": 3.4238, + "step": 1838592 + }, + { + "epoch": 1.0, + "learning_rate": 1.989102526725294e-05, + "loss": 3.4218, + "step": 1839104 + }, + { + "epoch": 1.0, + "learning_rate": 1.988263931974242e-05, + "loss": 3.4238, + "step": 1839616 + }, + { + "epoch": 1.0, + "learning_rate": 1.9874253372231904e-05, + "loss": 3.419, + "step": 1840128 + }, + { + "epoch": 1.0, + "learning_rate": 1.9865867424721383e-05, + "loss": 3.4226, + "step": 1840640 + }, + { + "epoch": 1.0, + "learning_rate": 1.985748147721086e-05, + "loss": 3.4273, + "step": 1841152 + }, + { + "epoch": 1.0, + "learning_rate": 1.984909552970034e-05, + "loss": 3.4335, + "step": 1841664 + }, + { + "epoch": 1.0, + "learning_rate": 1.984070958218982e-05, + "loss": 3.4322, + "step": 1842176 + }, + { + "epoch": 1.0, + "learning_rate": 1.9832340013483032e-05, + "loss": 3.4362, + "step": 1842688 + }, + { + "epoch": 1.0, + "learning_rate": 1.9823954065972512e-05, + "loss": 3.4211, + "step": 1843200 + }, + { + "epoch": 1.0, + "learning_rate": 1.9815568118461992e-05, + "loss": 3.4304, + "step": 1843712 + }, + { + "epoch": 1.0, + "learning_rate": 1.9807198549755205e-05, + "loss": 3.424, + "step": 1844224 + }, + { + "epoch": 1.0, + "learning_rate": 1.9798812602244685e-05, + "loss": 3.4366, + "step": 1844736 + }, + { + "epoch": 1.0, + "learning_rate": 1.979042665473416e-05, + "loss": 3.4232, + "step": 1845248 + }, + { + "epoch": 1.0, + "learning_rate": 1.978204070722364e-05, + "loss": 3.4213, + "step": 1845760 + }, + { + "epoch": 1.0, + "learning_rate": 1.977365475971312e-05, + "loss": 3.4179, + "step": 1846272 + }, + { + "epoch": 1.0, + "learning_rate": 1.9765268812202605e-05, + "loss": 3.4184, + "step": 1846784 + }, + { + "epoch": 1.01, + "learning_rate": 1.9756882864692085e-05, + "loss": 3.4164, + "step": 1847296 + }, + { + "epoch": 1.01, + "learning_rate": 1.9748496917181565e-05, + "loss": 3.4311, + "step": 1847808 + }, + { + "epoch": 1.01, + "learning_rate": 1.9740127348474774e-05, + "loss": 3.4322, + "step": 1848320 + }, + { + "epoch": 1.01, + "learning_rate": 1.9731741400964254e-05, + "loss": 3.4317, + "step": 1848832 + }, + { + "epoch": 1.01, + "learning_rate": 1.9723355453453734e-05, + "loss": 3.4229, + "step": 1849344 + }, + { + "epoch": 1.01, + "learning_rate": 1.9714969505943213e-05, + "loss": 3.4354, + "step": 1849856 + }, + { + "epoch": 1.01, + "learning_rate": 1.970661631604016e-05, + "loss": 3.4318, + "step": 1850368 + }, + { + "epoch": 1.01, + "learning_rate": 1.9698230368529635e-05, + "loss": 3.417, + "step": 1850880 + }, + { + "epoch": 1.01, + "learning_rate": 1.9689844421019115e-05, + "loss": 3.4153, + "step": 1851392 + }, + { + "epoch": 1.01, + "learning_rate": 1.9681458473508595e-05, + "loss": 3.4199, + "step": 1851904 + }, + { + "epoch": 1.01, + "learning_rate": 1.9673072525998075e-05, + "loss": 3.4236, + "step": 1852416 + }, + { + "epoch": 1.01, + "learning_rate": 1.9664702957291287e-05, + "loss": 3.4304, + "step": 1852928 + }, + { + "epoch": 1.01, + "learning_rate": 1.9656317009780767e-05, + "loss": 3.4236, + "step": 1853440 + }, + { + "epoch": 1.01, + "learning_rate": 1.9647931062270247e-05, + "loss": 3.4185, + "step": 1853952 + }, + { + "epoch": 1.01, + "learning_rate": 1.9639545114759727e-05, + "loss": 3.4343, + "step": 1854464 + }, + { + "epoch": 1.01, + "learning_rate": 1.9631159167249207e-05, + "loss": 3.4221, + "step": 1854976 + }, + { + "epoch": 1.01, + "learning_rate": 1.9622773219738687e-05, + "loss": 3.425, + "step": 1855488 + }, + { + "epoch": 1.01, + "learning_rate": 1.9614387272228167e-05, + "loss": 3.4127, + "step": 1856000 + }, + { + "epoch": 1.01, + "learning_rate": 1.960601770352138e-05, + "loss": 3.4022, + "step": 1856512 + }, + { + "epoch": 1.01, + "learning_rate": 1.959763175601086e-05, + "loss": 3.4366, + "step": 1857024 + }, + { + "epoch": 1.01, + "learning_rate": 1.9589245808500336e-05, + "loss": 3.4205, + "step": 1857536 + }, + { + "epoch": 1.01, + "learning_rate": 1.9580859860989816e-05, + "loss": 3.4266, + "step": 1858048 + }, + { + "epoch": 1.01, + "learning_rate": 1.9572473913479296e-05, + "loss": 3.4205, + "step": 1858560 + }, + { + "epoch": 1.01, + "learning_rate": 1.9564104344772512e-05, + "loss": 3.4168, + "step": 1859072 + }, + { + "epoch": 1.01, + "learning_rate": 1.955571839726199e-05, + "loss": 3.4091, + "step": 1859584 + }, + { + "epoch": 1.01, + "learning_rate": 1.954733244975147e-05, + "loss": 3.4242, + "step": 1860096 + }, + { + "epoch": 1.01, + "learning_rate": 1.953894650224095e-05, + "loss": 3.4148, + "step": 1860608 + }, + { + "epoch": 1.01, + "learning_rate": 1.953056055473043e-05, + "loss": 3.4195, + "step": 1861120 + }, + { + "epoch": 1.01, + "learning_rate": 1.952217460721991e-05, + "loss": 3.4275, + "step": 1861632 + }, + { + "epoch": 1.01, + "learning_rate": 1.951380503851312e-05, + "loss": 3.4149, + "step": 1862144 + }, + { + "epoch": 1.01, + "learning_rate": 1.95054190910026e-05, + "loss": 3.4144, + "step": 1862656 + }, + { + "epoch": 1.01, + "learning_rate": 1.949703314349208e-05, + "loss": 3.4292, + "step": 1863168 + }, + { + "epoch": 1.01, + "learning_rate": 1.948864719598156e-05, + "loss": 3.4132, + "step": 1863680 + }, + { + "epoch": 1.01, + "learning_rate": 1.948026124847104e-05, + "loss": 3.414, + "step": 1864192 + }, + { + "epoch": 1.01, + "learning_rate": 1.9471875300960517e-05, + "loss": 3.4307, + "step": 1864704 + }, + { + "epoch": 1.01, + "learning_rate": 1.946350573225373e-05, + "loss": 3.4219, + "step": 1865216 + }, + { + "epoch": 1.01, + "learning_rate": 1.9455119784743213e-05, + "loss": 3.4119, + "step": 1865728 + }, + { + "epoch": 1.01, + "learning_rate": 1.9446733837232693e-05, + "loss": 3.421, + "step": 1866240 + }, + { + "epoch": 1.01, + "learning_rate": 1.943834788972217e-05, + "loss": 3.4109, + "step": 1866752 + }, + { + "epoch": 1.01, + "learning_rate": 1.9429978321015382e-05, + "loss": 3.4092, + "step": 1867264 + }, + { + "epoch": 1.01, + "learning_rate": 1.9421592373504862e-05, + "loss": 3.43, + "step": 1867776 + }, + { + "epoch": 1.01, + "learning_rate": 1.9413206425994342e-05, + "loss": 3.4199, + "step": 1868288 + }, + { + "epoch": 1.01, + "learning_rate": 1.9404820478483822e-05, + "loss": 3.4269, + "step": 1868800 + }, + { + "epoch": 1.01, + "learning_rate": 1.9396434530973302e-05, + "loss": 3.4231, + "step": 1869312 + }, + { + "epoch": 1.01, + "learning_rate": 1.9388048583462782e-05, + "loss": 3.4404, + "step": 1869824 + }, + { + "epoch": 1.01, + "learning_rate": 1.9379662635952262e-05, + "loss": 3.4158, + "step": 1870336 + }, + { + "epoch": 1.01, + "learning_rate": 1.9371276688441742e-05, + "loss": 3.4279, + "step": 1870848 + }, + { + "epoch": 1.01, + "learning_rate": 1.936290711973495e-05, + "loss": 3.4277, + "step": 1871360 + }, + { + "epoch": 1.01, + "learning_rate": 1.935452117222443e-05, + "loss": 3.4168, + "step": 1871872 + }, + { + "epoch": 1.01, + "learning_rate": 1.9346135224713914e-05, + "loss": 3.4194, + "step": 1872384 + }, + { + "epoch": 1.01, + "learning_rate": 1.9337749277203394e-05, + "loss": 3.4327, + "step": 1872896 + }, + { + "epoch": 1.01, + "learning_rate": 1.9329363329692874e-05, + "loss": 3.4272, + "step": 1873408 + }, + { + "epoch": 1.01, + "learning_rate": 1.932097738218235e-05, + "loss": 3.4302, + "step": 1873920 + }, + { + "epoch": 1.01, + "learning_rate": 1.9312607813475563e-05, + "loss": 3.4109, + "step": 1874432 + }, + { + "epoch": 1.01, + "learning_rate": 1.9304221865965043e-05, + "loss": 3.4039, + "step": 1874944 + }, + { + "epoch": 1.01, + "learning_rate": 1.9295835918454523e-05, + "loss": 3.4229, + "step": 1875456 + }, + { + "epoch": 1.01, + "learning_rate": 1.9287449970944003e-05, + "loss": 3.431, + "step": 1875968 + }, + { + "epoch": 1.01, + "learning_rate": 1.9279080402237215e-05, + "loss": 3.4265, + "step": 1876480 + }, + { + "epoch": 1.01, + "learning_rate": 1.9270694454726695e-05, + "loss": 3.4224, + "step": 1876992 + }, + { + "epoch": 1.02, + "learning_rate": 1.9262308507216172e-05, + "loss": 3.4097, + "step": 1877504 + }, + { + "epoch": 1.02, + "learning_rate": 1.9253922559705652e-05, + "loss": 3.4213, + "step": 1878016 + }, + { + "epoch": 1.02, + "learning_rate": 1.9245536612195135e-05, + "loss": 3.417, + "step": 1878528 + }, + { + "epoch": 1.02, + "learning_rate": 1.9237150664684615e-05, + "loss": 3.4165, + "step": 1879040 + }, + { + "epoch": 1.02, + "learning_rate": 1.9228764717174095e-05, + "loss": 3.4305, + "step": 1879552 + }, + { + "epoch": 1.02, + "learning_rate": 1.9220395148467304e-05, + "loss": 3.4358, + "step": 1880064 + }, + { + "epoch": 1.02, + "learning_rate": 1.9212009200956784e-05, + "loss": 3.4292, + "step": 1880576 + }, + { + "epoch": 1.02, + "learning_rate": 1.9203623253446264e-05, + "loss": 3.4174, + "step": 1881088 + }, + { + "epoch": 1.02, + "learning_rate": 1.9195237305935744e-05, + "loss": 3.4185, + "step": 1881600 + }, + { + "epoch": 1.02, + "learning_rate": 1.9186867737228957e-05, + "loss": 3.4207, + "step": 1882112 + }, + { + "epoch": 1.02, + "learning_rate": 1.9178481789718437e-05, + "loss": 3.4296, + "step": 1882624 + }, + { + "epoch": 1.02, + "learning_rate": 1.9170095842207917e-05, + "loss": 3.4202, + "step": 1883136 + }, + { + "epoch": 1.02, + "learning_rate": 1.9161709894697396e-05, + "loss": 3.4296, + "step": 1883648 + }, + { + "epoch": 1.02, + "learning_rate": 1.9153323947186876e-05, + "loss": 3.422, + "step": 1884160 + }, + { + "epoch": 1.02, + "learning_rate": 1.9144937999676353e-05, + "loss": 3.4138, + "step": 1884672 + }, + { + "epoch": 1.02, + "learning_rate": 1.9136552052165836e-05, + "loss": 3.4217, + "step": 1885184 + }, + { + "epoch": 1.02, + "learning_rate": 1.9128166104655316e-05, + "loss": 3.4139, + "step": 1885696 + }, + { + "epoch": 1.02, + "learning_rate": 1.911979653594853e-05, + "loss": 3.4149, + "step": 1886208 + }, + { + "epoch": 1.02, + "learning_rate": 1.9111410588438005e-05, + "loss": 3.4231, + "step": 1886720 + }, + { + "epoch": 1.02, + "learning_rate": 1.9103024640927485e-05, + "loss": 3.4216, + "step": 1887232 + }, + { + "epoch": 1.02, + "learning_rate": 1.9094638693416965e-05, + "loss": 3.4139, + "step": 1887744 + }, + { + "epoch": 1.02, + "learning_rate": 1.9086269124710178e-05, + "loss": 3.4143, + "step": 1888256 + }, + { + "epoch": 1.02, + "learning_rate": 1.9077883177199658e-05, + "loss": 3.4115, + "step": 1888768 + }, + { + "epoch": 1.02, + "learning_rate": 1.906951360849287e-05, + "loss": 3.4254, + "step": 1889280 + }, + { + "epoch": 1.02, + "learning_rate": 1.906112766098235e-05, + "loss": 3.4154, + "step": 1889792 + }, + { + "epoch": 1.02, + "learning_rate": 1.9052741713471827e-05, + "loss": 3.4354, + "step": 1890304 + }, + { + "epoch": 1.02, + "learning_rate": 1.9044355765961307e-05, + "loss": 3.4339, + "step": 1890816 + }, + { + "epoch": 1.02, + "learning_rate": 1.903596981845079e-05, + "loss": 3.4286, + "step": 1891328 + }, + { + "epoch": 1.02, + "learning_rate": 1.902758387094027e-05, + "loss": 3.4201, + "step": 1891840 + }, + { + "epoch": 1.02, + "learning_rate": 1.901919792342975e-05, + "loss": 3.4159, + "step": 1892352 + }, + { + "epoch": 1.02, + "learning_rate": 1.901082835472296e-05, + "loss": 3.4244, + "step": 1892864 + }, + { + "epoch": 1.02, + "learning_rate": 1.900244240721244e-05, + "loss": 3.4188, + "step": 1893376 + }, + { + "epoch": 1.02, + "learning_rate": 1.899405645970192e-05, + "loss": 3.4127, + "step": 1893888 + }, + { + "epoch": 1.02, + "learning_rate": 1.89856705121914e-05, + "loss": 3.4169, + "step": 1894400 + }, + { + "epoch": 1.02, + "learning_rate": 1.8977284564680882e-05, + "loss": 3.4243, + "step": 1894912 + }, + { + "epoch": 1.02, + "learning_rate": 1.896889861717036e-05, + "loss": 3.4133, + "step": 1895424 + }, + { + "epoch": 1.02, + "learning_rate": 1.896051266965984e-05, + "loss": 3.4187, + "step": 1895936 + }, + { + "epoch": 1.02, + "learning_rate": 1.895214310095305e-05, + "loss": 3.4131, + "step": 1896448 + }, + { + "epoch": 1.02, + "learning_rate": 1.894375715344253e-05, + "loss": 3.4262, + "step": 1896960 + }, + { + "epoch": 1.02, + "learning_rate": 1.8935371205932008e-05, + "loss": 3.4114, + "step": 1897472 + }, + { + "epoch": 1.02, + "learning_rate": 1.892698525842149e-05, + "loss": 3.4276, + "step": 1897984 + }, + { + "epoch": 1.02, + "learning_rate": 1.8918615689714704e-05, + "loss": 3.4267, + "step": 1898496 + }, + { + "epoch": 1.02, + "learning_rate": 1.8910229742204184e-05, + "loss": 3.4324, + "step": 1899008 + }, + { + "epoch": 1.02, + "learning_rate": 1.890184379469366e-05, + "loss": 3.4105, + "step": 1899520 + }, + { + "epoch": 1.02, + "learning_rate": 1.889345784718314e-05, + "loss": 3.4264, + "step": 1900032 + }, + { + "epoch": 1.02, + "learning_rate": 1.888507189967262e-05, + "loss": 3.4157, + "step": 1900544 + }, + { + "epoch": 1.02, + "learning_rate": 1.88766859521621e-05, + "loss": 3.4257, + "step": 1901056 + }, + { + "epoch": 1.02, + "learning_rate": 1.8868300004651583e-05, + "loss": 3.4247, + "step": 1901568 + }, + { + "epoch": 1.02, + "learning_rate": 1.8859914057141063e-05, + "loss": 3.4157, + "step": 1902080 + }, + { + "epoch": 1.02, + "learning_rate": 1.8851544488434272e-05, + "loss": 3.4203, + "step": 1902592 + }, + { + "epoch": 1.02, + "learning_rate": 1.8843158540923752e-05, + "loss": 3.4339, + "step": 1903104 + }, + { + "epoch": 1.02, + "learning_rate": 1.8834772593413232e-05, + "loss": 3.4102, + "step": 1903616 + }, + { + "epoch": 1.02, + "learning_rate": 1.8826403024706445e-05, + "loss": 3.4213, + "step": 1904128 + }, + { + "epoch": 1.02, + "learning_rate": 1.8818017077195925e-05, + "loss": 3.4248, + "step": 1904640 + }, + { + "epoch": 1.02, + "learning_rate": 1.8809631129685405e-05, + "loss": 3.4227, + "step": 1905152 + }, + { + "epoch": 1.02, + "learning_rate": 1.8801245182174885e-05, + "loss": 3.4142, + "step": 1905664 + }, + { + "epoch": 1.02, + "learning_rate": 1.8792875613468094e-05, + "loss": 3.4223, + "step": 1906176 + }, + { + "epoch": 1.02, + "learning_rate": 1.8784489665957574e-05, + "loss": 3.4278, + "step": 1906688 + }, + { + "epoch": 1.02, + "learning_rate": 1.8776103718447054e-05, + "loss": 3.4051, + "step": 1907200 + }, + { + "epoch": 1.02, + "learning_rate": 1.8767717770936537e-05, + "loss": 3.4238, + "step": 1907712 + }, + { + "epoch": 1.03, + "eval_loss": 3.8556225299835205, + "eval_runtime": 305.349, + "eval_samples_per_second": 1249.688, + "eval_steps_per_second": 39.054, + "step": 1908000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8759331823426014e-05, + "loss": 3.4138, + "step": 1908224 + }, + { + "epoch": 0.0, + "learning_rate": 1.8750945875915494e-05, + "loss": 3.4151, + "step": 1908736 + }, + { + "epoch": 0.0, + "learning_rate": 1.8742559928404973e-05, + "loss": 3.4159, + "step": 1909248 + }, + { + "epoch": 0.0, + "learning_rate": 1.8734173980894453e-05, + "loss": 3.4248, + "step": 1909760 + }, + { + "epoch": 0.0, + "learning_rate": 1.8725804412187663e-05, + "loss": 3.4373, + "step": 1910272 + }, + { + "epoch": 0.0, + "learning_rate": 1.871743484348088e-05, + "loss": 3.4178, + "step": 1910784 + }, + { + "epoch": 0.0, + "learning_rate": 1.870904889597036e-05, + "loss": 3.4156, + "step": 1911296 + }, + { + "epoch": 0.0, + "learning_rate": 1.870066294845984e-05, + "loss": 3.4185, + "step": 1911808 + }, + { + "epoch": 0.0, + "learning_rate": 1.8692277000949315e-05, + "loss": 3.4072, + "step": 1912320 + }, + { + "epoch": 0.0, + "learning_rate": 1.8683891053438795e-05, + "loss": 3.4271, + "step": 1912832 + }, + { + "epoch": 0.0, + "learning_rate": 1.8675505105928275e-05, + "loss": 3.4127, + "step": 1913344 + }, + { + "epoch": 0.0, + "learning_rate": 1.8667119158417755e-05, + "loss": 3.4205, + "step": 1913856 + }, + { + "epoch": 0.0, + "learning_rate": 1.8658749589710967e-05, + "loss": 3.4234, + "step": 1914368 + }, + { + "epoch": 0.0, + "learning_rate": 1.8650363642200447e-05, + "loss": 3.408, + "step": 1914880 + }, + { + "epoch": 0.0, + "learning_rate": 1.8641977694689927e-05, + "loss": 3.4083, + "step": 1915392 + }, + { + "epoch": 0.0, + "learning_rate": 1.8633591747179407e-05, + "loss": 3.4123, + "step": 1915904 + }, + { + "epoch": 0.0, + "learning_rate": 1.8625205799668887e-05, + "loss": 3.4091, + "step": 1916416 + }, + { + "epoch": 0.0, + "learning_rate": 1.8616819852158367e-05, + "loss": 3.4169, + "step": 1916928 + }, + { + "epoch": 0.0, + "learning_rate": 1.8608433904647847e-05, + "loss": 3.4115, + "step": 1917440 + }, + { + "epoch": 0.0, + "learning_rate": 1.8600047957137327e-05, + "loss": 3.4208, + "step": 1917952 + }, + { + "epoch": 0.0, + "learning_rate": 1.859167838843054e-05, + "loss": 3.4226, + "step": 1918464 + }, + { + "epoch": 0.0, + "learning_rate": 1.858330881972375e-05, + "loss": 3.425, + "step": 1918976 + }, + { + "epoch": 0.0, + "learning_rate": 1.857492287221323e-05, + "loss": 3.4158, + "step": 1919488 + }, + { + "epoch": 0.0, + "learning_rate": 1.856653692470271e-05, + "loss": 3.4118, + "step": 1920000 + }, + { + "epoch": 0.0, + "learning_rate": 1.8558150977192192e-05, + "loss": 3.416, + "step": 1920512 + }, + { + "epoch": 0.0, + "learning_rate": 1.854976502968167e-05, + "loss": 3.426, + "step": 1921024 + }, + { + "epoch": 0.0, + "learning_rate": 1.8541379082171148e-05, + "loss": 3.4131, + "step": 1921536 + }, + { + "epoch": 0.0, + "learning_rate": 1.853300951346436e-05, + "loss": 3.4115, + "step": 1922048 + }, + { + "epoch": 0.0, + "learning_rate": 1.852462356595384e-05, + "loss": 3.4088, + "step": 1922560 + }, + { + "epoch": 0.0, + "learning_rate": 1.8516237618443317e-05, + "loss": 3.4071, + "step": 1923072 + }, + { + "epoch": 0.01, + "learning_rate": 1.85078516709328e-05, + "loss": 3.4068, + "step": 1923584 + }, + { + "epoch": 0.01, + "learning_rate": 1.849946572342228e-05, + "loss": 3.4223, + "step": 1924096 + }, + { + "epoch": 0.01, + "learning_rate": 1.849107977591176e-05, + "loss": 3.4236, + "step": 1924608 + }, + { + "epoch": 0.01, + "learning_rate": 1.848269382840124e-05, + "loss": 3.4232, + "step": 1925120 + }, + { + "epoch": 0.01, + "learning_rate": 1.847430788089072e-05, + "loss": 3.4118, + "step": 1925632 + }, + { + "epoch": 0.01, + "learning_rate": 1.846593831218393e-05, + "loss": 3.4158, + "step": 1926144 + }, + { + "epoch": 0.01, + "learning_rate": 1.8457568743477142e-05, + "loss": 3.4278, + "step": 1926656 + }, + { + "epoch": 0.01, + "learning_rate": 1.8449182795966622e-05, + "loss": 3.407, + "step": 1927168 + }, + { + "epoch": 0.01, + "learning_rate": 1.8440796848456102e-05, + "loss": 3.4072, + "step": 1927680 + }, + { + "epoch": 0.01, + "learning_rate": 1.8432410900945582e-05, + "loss": 3.4063, + "step": 1928192 + }, + { + "epoch": 0.01, + "learning_rate": 1.8424024953435062e-05, + "loss": 3.4117, + "step": 1928704 + }, + { + "epoch": 0.01, + "learning_rate": 1.841565538472827e-05, + "loss": 3.419, + "step": 1929216 + }, + { + "epoch": 0.01, + "learning_rate": 1.8407269437217754e-05, + "loss": 3.413, + "step": 1929728 + }, + { + "epoch": 0.01, + "learning_rate": 1.8398883489707234e-05, + "loss": 3.4098, + "step": 1930240 + }, + { + "epoch": 0.01, + "learning_rate": 1.8390497542196714e-05, + "loss": 3.4225, + "step": 1930752 + }, + { + "epoch": 0.01, + "learning_rate": 1.8382111594686194e-05, + "loss": 3.4143, + "step": 1931264 + }, + { + "epoch": 0.01, + "learning_rate": 1.837372564717567e-05, + "loss": 3.4126, + "step": 1931776 + }, + { + "epoch": 0.01, + "learning_rate": 1.836533969966515e-05, + "loss": 3.4051, + "step": 1932288 + }, + { + "epoch": 0.01, + "learning_rate": 1.8356970130958363e-05, + "loss": 3.3846, + "step": 1932800 + }, + { + "epoch": 0.01, + "learning_rate": 1.8348584183447847e-05, + "loss": 3.4287, + "step": 1933312 + }, + { + "epoch": 0.01, + "learning_rate": 1.8340198235937323e-05, + "loss": 3.4086, + "step": 1933824 + }, + { + "epoch": 0.01, + "learning_rate": 1.8331812288426803e-05, + "loss": 3.4182, + "step": 1934336 + }, + { + "epoch": 0.01, + "learning_rate": 1.8323426340916283e-05, + "loss": 3.4059, + "step": 1934848 + }, + { + "epoch": 0.01, + "learning_rate": 1.8315056772209495e-05, + "loss": 3.4083, + "step": 1935360 + }, + { + "epoch": 0.01, + "learning_rate": 1.8306670824698975e-05, + "loss": 3.399, + "step": 1935872 + }, + { + "epoch": 0.01, + "learning_rate": 1.8298284877188455e-05, + "loss": 3.4118, + "step": 1936384 + }, + { + "epoch": 0.01, + "learning_rate": 1.8289898929677935e-05, + "loss": 3.4045, + "step": 1936896 + }, + { + "epoch": 0.01, + "learning_rate": 1.8281512982167415e-05, + "loss": 3.41, + "step": 1937408 + }, + { + "epoch": 0.01, + "learning_rate": 1.8273127034656895e-05, + "loss": 3.4197, + "step": 1937920 + }, + { + "epoch": 0.01, + "learning_rate": 1.8264757465950104e-05, + "loss": 3.4042, + "step": 1938432 + }, + { + "epoch": 0.01, + "learning_rate": 1.8256371518439584e-05, + "loss": 3.4028, + "step": 1938944 + }, + { + "epoch": 0.01, + "learning_rate": 1.8247985570929064e-05, + "loss": 3.4197, + "step": 1939456 + }, + { + "epoch": 0.01, + "learning_rate": 1.8239599623418548e-05, + "loss": 3.4046, + "step": 1939968 + }, + { + "epoch": 0.01, + "learning_rate": 1.8231213675908028e-05, + "loss": 3.4024, + "step": 1940480 + }, + { + "epoch": 0.01, + "learning_rate": 1.8222827728397504e-05, + "loss": 3.4173, + "step": 1940992 + }, + { + "epoch": 0.01, + "learning_rate": 1.8214458159690717e-05, + "loss": 3.4133, + "step": 1941504 + }, + { + "epoch": 0.01, + "learning_rate": 1.8206072212180197e-05, + "loss": 3.4003, + "step": 1942016 + }, + { + "epoch": 0.01, + "learning_rate": 1.8197686264669677e-05, + "loss": 3.4092, + "step": 1942528 + }, + { + "epoch": 0.01, + "learning_rate": 1.8189300317159156e-05, + "loss": 3.4002, + "step": 1943040 + }, + { + "epoch": 0.01, + "learning_rate": 1.818093074845237e-05, + "loss": 3.403, + "step": 1943552 + }, + { + "epoch": 0.01, + "learning_rate": 1.817254480094185e-05, + "loss": 3.4178, + "step": 1944064 + }, + { + "epoch": 0.01, + "learning_rate": 1.8164158853431325e-05, + "loss": 3.4105, + "step": 1944576 + }, + { + "epoch": 0.01, + "learning_rate": 1.8155772905920805e-05, + "loss": 3.4184, + "step": 1945088 + }, + { + "epoch": 0.01, + "learning_rate": 1.8147386958410285e-05, + "loss": 3.4134, + "step": 1945600 + }, + { + "epoch": 0.01, + "learning_rate": 1.813900101089977e-05, + "loss": 3.429, + "step": 1946112 + }, + { + "epoch": 0.01, + "learning_rate": 1.813061506338925e-05, + "loss": 3.4028, + "step": 1946624 + }, + { + "epoch": 0.01, + "learning_rate": 1.812222911587873e-05, + "loss": 3.4238, + "step": 1947136 + }, + { + "epoch": 0.01, + "learning_rate": 1.8113859547171938e-05, + "loss": 3.4105, + "step": 1947648 + }, + { + "epoch": 0.01, + "learning_rate": 1.8105473599661418e-05, + "loss": 3.4093, + "step": 1948160 + }, + { + "epoch": 0.01, + "learning_rate": 1.8097087652150898e-05, + "loss": 3.409, + "step": 1948672 + }, + { + "epoch": 0.01, + "learning_rate": 1.8088701704640378e-05, + "loss": 3.4217, + "step": 1949184 + }, + { + "epoch": 0.01, + "learning_rate": 1.808033213593359e-05, + "loss": 3.4186, + "step": 1949696 + }, + { + "epoch": 0.01, + "learning_rate": 1.807194618842307e-05, + "loss": 3.4188, + "step": 1950208 + }, + { + "epoch": 0.01, + "learning_rate": 1.806356024091255e-05, + "loss": 3.3998, + "step": 1950720 + }, + { + "epoch": 0.01, + "learning_rate": 1.805517429340203e-05, + "loss": 3.3977, + "step": 1951232 + }, + { + "epoch": 0.01, + "learning_rate": 1.8046788345891507e-05, + "loss": 3.4118, + "step": 1951744 + }, + { + "epoch": 0.01, + "learning_rate": 1.8038402398380986e-05, + "loss": 3.4187, + "step": 1952256 + }, + { + "epoch": 0.01, + "learning_rate": 1.803001645087047e-05, + "loss": 3.4116, + "step": 1952768 + }, + { + "epoch": 0.01, + "learning_rate": 1.802163050335995e-05, + "loss": 3.4151, + "step": 1953280 + }, + { + "epoch": 0.02, + "learning_rate": 1.801326093465316e-05, + "loss": 3.4038, + "step": 1953792 + }, + { + "epoch": 0.02, + "learning_rate": 1.800487498714264e-05, + "loss": 3.4083, + "step": 1954304 + }, + { + "epoch": 0.02, + "learning_rate": 1.799648903963212e-05, + "loss": 3.4086, + "step": 1954816 + }, + { + "epoch": 0.02, + "learning_rate": 1.79881030921216e-05, + "loss": 3.4027, + "step": 1955328 + }, + { + "epoch": 0.02, + "learning_rate": 1.797973352341481e-05, + "loss": 3.4196, + "step": 1955840 + }, + { + "epoch": 0.02, + "learning_rate": 1.7971363954708024e-05, + "loss": 3.4263, + "step": 1956352 + }, + { + "epoch": 0.02, + "learning_rate": 1.7962978007197504e-05, + "loss": 3.4181, + "step": 1956864 + }, + { + "epoch": 0.02, + "learning_rate": 1.795459205968698e-05, + "loss": 3.4049, + "step": 1957376 + }, + { + "epoch": 0.02, + "learning_rate": 1.794620611217646e-05, + "loss": 3.4082, + "step": 1957888 + }, + { + "epoch": 0.02, + "learning_rate": 1.793782016466594e-05, + "loss": 3.4129, + "step": 1958400 + }, + { + "epoch": 0.02, + "learning_rate": 1.7929450595959156e-05, + "loss": 3.4185, + "step": 1958912 + }, + { + "epoch": 0.02, + "learning_rate": 1.7921064648448633e-05, + "loss": 3.4097, + "step": 1959424 + }, + { + "epoch": 0.02, + "learning_rate": 1.7912678700938113e-05, + "loss": 3.4188, + "step": 1959936 + }, + { + "epoch": 0.02, + "learning_rate": 1.7904292753427593e-05, + "loss": 3.4127, + "step": 1960448 + }, + { + "epoch": 0.02, + "learning_rate": 1.7895906805917072e-05, + "loss": 3.4064, + "step": 1960960 + }, + { + "epoch": 0.02, + "learning_rate": 1.7887520858406552e-05, + "loss": 3.4112, + "step": 1961472 + }, + { + "epoch": 0.02, + "learning_rate": 1.7879134910896032e-05, + "loss": 3.4003, + "step": 1961984 + }, + { + "epoch": 0.02, + "learning_rate": 1.7870748963385516e-05, + "loss": 3.4045, + "step": 1962496 + }, + { + "epoch": 0.02, + "learning_rate": 1.7862379394678725e-05, + "loss": 3.4151, + "step": 1963008 + }, + { + "epoch": 0.02, + "learning_rate": 1.7853993447168205e-05, + "loss": 3.4132, + "step": 1963520 + }, + { + "epoch": 0.02, + "learning_rate": 1.7845607499657685e-05, + "loss": 3.4019, + "step": 1964032 + }, + { + "epoch": 0.02, + "learning_rate": 1.783722155214716e-05, + "loss": 3.4045, + "step": 1964544 + }, + { + "epoch": 0.02, + "learning_rate": 1.7828851983440377e-05, + "loss": 3.3966, + "step": 1965056 + }, + { + "epoch": 0.02, + "learning_rate": 1.7820482414733586e-05, + "loss": 3.418, + "step": 1965568 + }, + { + "epoch": 0.02, + "learning_rate": 1.7812096467223066e-05, + "loss": 3.4042, + "step": 1966080 + }, + { + "epoch": 0.02, + "learning_rate": 1.7803710519712546e-05, + "loss": 3.4244, + "step": 1966592 + }, + { + "epoch": 0.02, + "learning_rate": 1.7795324572202026e-05, + "loss": 3.4178, + "step": 1967104 + }, + { + "epoch": 0.02, + "learning_rate": 1.7786938624691506e-05, + "loss": 3.423, + "step": 1967616 + }, + { + "epoch": 0.02, + "learning_rate": 1.7778552677180986e-05, + "loss": 3.4067, + "step": 1968128 + }, + { + "epoch": 0.02, + "learning_rate": 1.77701831084742e-05, + "loss": 3.406, + "step": 1968640 + }, + { + "epoch": 0.02, + "learning_rate": 1.776179716096368e-05, + "loss": 3.4142, + "step": 1969152 + }, + { + "epoch": 0.02, + "learning_rate": 1.775341121345316e-05, + "loss": 3.4116, + "step": 1969664 + }, + { + "epoch": 0.02, + "learning_rate": 1.7745025265942635e-05, + "loss": 3.4014, + "step": 1970176 + }, + { + "epoch": 0.02, + "learning_rate": 1.7736639318432115e-05, + "loss": 3.4036, + "step": 1970688 + }, + { + "epoch": 0.02, + "learning_rate": 1.7728253370921595e-05, + "loss": 3.4134, + "step": 1971200 + }, + { + "epoch": 0.02, + "learning_rate": 1.771988380221481e-05, + "loss": 3.4058, + "step": 1971712 + }, + { + "epoch": 0.02, + "learning_rate": 1.7711497854704287e-05, + "loss": 3.4073, + "step": 1972224 + }, + { + "epoch": 0.02, + "learning_rate": 1.7703111907193767e-05, + "loss": 3.4077, + "step": 1972736 + }, + { + "epoch": 0.02, + "learning_rate": 1.7694725959683247e-05, + "loss": 3.4102, + "step": 1973248 + }, + { + "epoch": 0.02, + "learning_rate": 1.7686340012172727e-05, + "loss": 3.4015, + "step": 1973760 + }, + { + "epoch": 0.02, + "learning_rate": 1.767797044346594e-05, + "loss": 3.4158, + "step": 1974272 + }, + { + "epoch": 0.02, + "learning_rate": 1.766958449595542e-05, + "loss": 3.413, + "step": 1974784 + }, + { + "epoch": 0.02, + "learning_rate": 1.76611985484449e-05, + "loss": 3.4275, + "step": 1975296 + }, + { + "epoch": 0.02, + "learning_rate": 1.765281260093438e-05, + "loss": 3.3996, + "step": 1975808 + }, + { + "epoch": 0.02, + "learning_rate": 1.764442665342386e-05, + "loss": 3.4153, + "step": 1976320 + }, + { + "epoch": 0.02, + "learning_rate": 1.763604070591334e-05, + "loss": 3.4055, + "step": 1976832 + }, + { + "epoch": 0.02, + "learning_rate": 1.7627654758402816e-05, + "loss": 3.4148, + "step": 1977344 + }, + { + "epoch": 0.02, + "learning_rate": 1.7619285189696032e-05, + "loss": 3.4113, + "step": 1977856 + }, + { + "epoch": 0.02, + "learning_rate": 1.7610899242185512e-05, + "loss": 3.4053, + "step": 1978368 + }, + { + "epoch": 0.02, + "learning_rate": 1.7602513294674992e-05, + "loss": 3.4102, + "step": 1978880 + }, + { + "epoch": 0.02, + "learning_rate": 1.759412734716447e-05, + "loss": 3.427, + "step": 1979392 + }, + { + "epoch": 0.02, + "learning_rate": 1.758574139965395e-05, + "loss": 3.3988, + "step": 1979904 + }, + { + "epoch": 0.02, + "learning_rate": 1.757735545214343e-05, + "loss": 3.4153, + "step": 1980416 + }, + { + "epoch": 0.02, + "learning_rate": 1.756898588343664e-05, + "loss": 3.4116, + "step": 1980928 + }, + { + "epoch": 0.02, + "learning_rate": 1.756059993592612e-05, + "loss": 3.4068, + "step": 1981440 + }, + { + "epoch": 0.02, + "learning_rate": 1.75522139884156e-05, + "loss": 3.4063, + "step": 1981952 + }, + { + "epoch": 0.02, + "learning_rate": 1.754382804090508e-05, + "loss": 3.4102, + "step": 1982464 + }, + { + "epoch": 0.02, + "learning_rate": 1.753544209339456e-05, + "loss": 3.4143, + "step": 1982976 + }, + { + "epoch": 0.02, + "learning_rate": 1.752705614588404e-05, + "loss": 3.4061, + "step": 1983488 + }, + { + "epoch": 0.02, + "learning_rate": 1.751868657717725e-05, + "loss": 3.4097, + "step": 1984000 + }, + { + "epoch": 0.03, + "eval_loss": 3.856940507888794, + "eval_runtime": 318.4977, + "eval_samples_per_second": 1198.096, + "eval_steps_per_second": 37.441, + "step": 1984320 + }, + { + "epoch": 1.0, + "learning_rate": 1.7510300629666733e-05, + "loss": 3.4047, + "step": 1984512 + }, + { + "epoch": 1.0, + "learning_rate": 1.7501914682156213e-05, + "loss": 3.4009, + "step": 1985024 + }, + { + "epoch": 1.0, + "learning_rate": 1.7493528734645693e-05, + "loss": 3.4071, + "step": 1985536 + }, + { + "epoch": 1.0, + "learning_rate": 1.7485142787135173e-05, + "loss": 3.4159, + "step": 1986048 + }, + { + "epoch": 1.0, + "learning_rate": 1.747675683962465e-05, + "loss": 3.4236, + "step": 1986560 + }, + { + "epoch": 1.0, + "learning_rate": 1.7468387270917862e-05, + "loss": 3.4095, + "step": 1987072 + }, + { + "epoch": 1.0, + "learning_rate": 1.7460001323407342e-05, + "loss": 3.4063, + "step": 1987584 + }, + { + "epoch": 1.0, + "learning_rate": 1.7451615375896822e-05, + "loss": 3.4049, + "step": 1988096 + }, + { + "epoch": 1.0, + "learning_rate": 1.7443229428386302e-05, + "loss": 3.4006, + "step": 1988608 + }, + { + "epoch": 1.0, + "learning_rate": 1.7434843480875782e-05, + "loss": 3.4143, + "step": 1989120 + }, + { + "epoch": 1.0, + "learning_rate": 1.7426457533365262e-05, + "loss": 3.4035, + "step": 1989632 + }, + { + "epoch": 1.0, + "learning_rate": 1.741807158585474e-05, + "loss": 3.4103, + "step": 1990144 + }, + { + "epoch": 1.0, + "learning_rate": 1.740970201714795e-05, + "loss": 3.4142, + "step": 1990656 + }, + { + "epoch": 1.0, + "learning_rate": 1.7401316069637434e-05, + "loss": 3.3984, + "step": 1991168 + }, + { + "epoch": 1.0, + "learning_rate": 1.7392930122126914e-05, + "loss": 3.398, + "step": 1991680 + }, + { + "epoch": 1.0, + "learning_rate": 1.7384544174616394e-05, + "loss": 3.398, + "step": 1992192 + }, + { + "epoch": 1.0, + "learning_rate": 1.7376158227105874e-05, + "loss": 3.4022, + "step": 1992704 + }, + { + "epoch": 1.0, + "learning_rate": 1.7367772279595354e-05, + "loss": 3.4028, + "step": 1993216 + }, + { + "epoch": 1.0, + "learning_rate": 1.735938633208483e-05, + "loss": 3.404, + "step": 1993728 + }, + { + "epoch": 1.0, + "learning_rate": 1.735100038457431e-05, + "loss": 3.4123, + "step": 1994240 + }, + { + "epoch": 1.0, + "learning_rate": 1.7342630815867526e-05, + "loss": 3.4122, + "step": 1994752 + }, + { + "epoch": 1.0, + "learning_rate": 1.7334261247160735e-05, + "loss": 3.4164, + "step": 1995264 + }, + { + "epoch": 1.0, + "learning_rate": 1.7325875299650215e-05, + "loss": 3.4061, + "step": 1995776 + }, + { + "epoch": 1.0, + "learning_rate": 1.7317489352139695e-05, + "loss": 3.4012, + "step": 1996288 + }, + { + "epoch": 1.0, + "learning_rate": 1.7309103404629175e-05, + "loss": 3.4084, + "step": 1996800 + }, + { + "epoch": 1.0, + "learning_rate": 1.7300717457118655e-05, + "loss": 3.4128, + "step": 1997312 + }, + { + "epoch": 1.0, + "learning_rate": 1.7292331509608135e-05, + "loss": 3.4012, + "step": 1997824 + }, + { + "epoch": 1.0, + "learning_rate": 1.7283961940901348e-05, + "loss": 3.4064, + "step": 1998336 + }, + { + "epoch": 1.0, + "learning_rate": 1.7275575993390828e-05, + "loss": 3.3971, + "step": 1998848 + }, + { + "epoch": 1.0, + "learning_rate": 1.7267190045880304e-05, + "loss": 3.3948, + "step": 1999360 + }, + { + "epoch": 1.01, + "learning_rate": 1.7258804098369784e-05, + "loss": 3.3988, + "step": 1999872 + }, + { + "epoch": 1.01, + "learning_rate": 1.7250418150859264e-05, + "loss": 3.4069, + "step": 2000384 + }, + { + "epoch": 1.01, + "learning_rate": 1.7242032203348747e-05, + "loss": 3.416, + "step": 2000896 + }, + { + "epoch": 1.01, + "learning_rate": 1.7233646255838227e-05, + "loss": 3.4102, + "step": 2001408 + }, + { + "epoch": 1.01, + "learning_rate": 1.7225276687131437e-05, + "loss": 3.407, + "step": 2001920 + }, + { + "epoch": 1.01, + "learning_rate": 1.7216890739620916e-05, + "loss": 3.4026, + "step": 2002432 + }, + { + "epoch": 1.01, + "learning_rate": 1.7208504792110396e-05, + "loss": 3.4195, + "step": 2002944 + }, + { + "epoch": 1.01, + "learning_rate": 1.7200118844599876e-05, + "loss": 3.4008, + "step": 2003456 + }, + { + "epoch": 1.01, + "learning_rate": 1.7191732897089356e-05, + "loss": 3.3955, + "step": 2003968 + }, + { + "epoch": 1.01, + "learning_rate": 1.7183346949578836e-05, + "loss": 3.395, + "step": 2004480 + }, + { + "epoch": 1.01, + "learning_rate": 1.7174961002068316e-05, + "loss": 3.4037, + "step": 2004992 + }, + { + "epoch": 1.01, + "learning_rate": 1.716659143336153e-05, + "loss": 3.4023, + "step": 2005504 + }, + { + "epoch": 1.01, + "learning_rate": 1.7158205485851005e-05, + "loss": 3.4069, + "step": 2006016 + }, + { + "epoch": 1.01, + "learning_rate": 1.7149819538340485e-05, + "loss": 3.4038, + "step": 2006528 + }, + { + "epoch": 1.01, + "learning_rate": 1.7141433590829965e-05, + "loss": 3.4081, + "step": 2007040 + }, + { + "epoch": 1.01, + "learning_rate": 1.713304764331945e-05, + "loss": 3.4047, + "step": 2007552 + }, + { + "epoch": 1.01, + "learning_rate": 1.712466169580893e-05, + "loss": 3.3998, + "step": 2008064 + }, + { + "epoch": 1.01, + "learning_rate": 1.711627574829841e-05, + "loss": 3.3974, + "step": 2008576 + }, + { + "epoch": 1.01, + "learning_rate": 1.7107906179591618e-05, + "loss": 3.3755, + "step": 2009088 + }, + { + "epoch": 1.01, + "learning_rate": 1.7099520232081098e-05, + "loss": 3.4158, + "step": 2009600 + }, + { + "epoch": 1.01, + "learning_rate": 1.7091134284570577e-05, + "loss": 3.3969, + "step": 2010112 + }, + { + "epoch": 1.01, + "learning_rate": 1.7082748337060057e-05, + "loss": 3.409, + "step": 2010624 + }, + { + "epoch": 1.01, + "learning_rate": 1.707436238954954e-05, + "loss": 3.3993, + "step": 2011136 + }, + { + "epoch": 1.01, + "learning_rate": 1.706599282084275e-05, + "loss": 3.3949, + "step": 2011648 + }, + { + "epoch": 1.01, + "learning_rate": 1.705760687333223e-05, + "loss": 3.3863, + "step": 2012160 + }, + { + "epoch": 1.01, + "learning_rate": 1.704922092582171e-05, + "loss": 3.4013, + "step": 2012672 + }, + { + "epoch": 1.01, + "learning_rate": 1.7040834978311186e-05, + "loss": 3.3987, + "step": 2013184 + }, + { + "epoch": 1.01, + "learning_rate": 1.7032449030800666e-05, + "loss": 3.3936, + "step": 2013696 + }, + { + "epoch": 1.01, + "learning_rate": 1.702406308329015e-05, + "loss": 3.4116, + "step": 2014208 + }, + { + "epoch": 1.01, + "learning_rate": 1.7015693514583362e-05, + "loss": 3.3987, + "step": 2014720 + }, + { + "epoch": 1.01, + "learning_rate": 1.700730756707284e-05, + "loss": 3.3868, + "step": 2015232 + }, + { + "epoch": 1.01, + "learning_rate": 1.699892161956232e-05, + "loss": 3.4068, + "step": 2015744 + }, + { + "epoch": 1.01, + "learning_rate": 1.69905356720518e-05, + "loss": 3.3948, + "step": 2016256 + }, + { + "epoch": 1.01, + "learning_rate": 1.698214972454128e-05, + "loss": 3.3941, + "step": 2016768 + }, + { + "epoch": 1.01, + "learning_rate": 1.697376377703076e-05, + "loss": 3.4064, + "step": 2017280 + }, + { + "epoch": 1.01, + "learning_rate": 1.6965377829520242e-05, + "loss": 3.4007, + "step": 2017792 + }, + { + "epoch": 1.01, + "learning_rate": 1.6956991882009722e-05, + "loss": 3.3892, + "step": 2018304 + }, + { + "epoch": 1.01, + "learning_rate": 1.694862231330293e-05, + "loss": 3.4024, + "step": 2018816 + }, + { + "epoch": 1.01, + "learning_rate": 1.694023636579241e-05, + "loss": 3.389, + "step": 2019328 + }, + { + "epoch": 1.01, + "learning_rate": 1.693185041828189e-05, + "loss": 3.3924, + "step": 2019840 + }, + { + "epoch": 1.01, + "learning_rate": 1.6923464470771367e-05, + "loss": 3.4064, + "step": 2020352 + }, + { + "epoch": 1.01, + "learning_rate": 1.6915094902064583e-05, + "loss": 3.4011, + "step": 2020864 + }, + { + "epoch": 1.01, + "learning_rate": 1.6906708954554063e-05, + "loss": 3.4078, + "step": 2021376 + }, + { + "epoch": 1.01, + "learning_rate": 1.6898339385847272e-05, + "loss": 3.3997, + "step": 2021888 + }, + { + "epoch": 1.01, + "learning_rate": 1.6889953438336752e-05, + "loss": 3.42, + "step": 2022400 + }, + { + "epoch": 1.01, + "learning_rate": 1.6881567490826232e-05, + "loss": 3.3958, + "step": 2022912 + }, + { + "epoch": 1.01, + "learning_rate": 1.6873181543315712e-05, + "loss": 3.4104, + "step": 2023424 + }, + { + "epoch": 1.01, + "learning_rate": 1.6864811974608925e-05, + "loss": 3.4004, + "step": 2023936 + }, + { + "epoch": 1.01, + "learning_rate": 1.6856426027098405e-05, + "loss": 3.3994, + "step": 2024448 + }, + { + "epoch": 1.01, + "learning_rate": 1.6848040079587885e-05, + "loss": 3.3969, + "step": 2024960 + }, + { + "epoch": 1.01, + "learning_rate": 1.6839654132077365e-05, + "loss": 3.4146, + "step": 2025472 + }, + { + "epoch": 1.01, + "learning_rate": 1.683126818456684e-05, + "loss": 3.4044, + "step": 2025984 + }, + { + "epoch": 1.01, + "learning_rate": 1.682288223705632e-05, + "loss": 3.4149, + "step": 2026496 + }, + { + "epoch": 1.01, + "learning_rate": 1.6814512668349537e-05, + "loss": 3.3866, + "step": 2027008 + }, + { + "epoch": 1.01, + "learning_rate": 1.6806126720839017e-05, + "loss": 3.3875, + "step": 2027520 + }, + { + "epoch": 1.01, + "learning_rate": 1.6797740773328493e-05, + "loss": 3.4016, + "step": 2028032 + }, + { + "epoch": 1.01, + "learning_rate": 1.6789354825817973e-05, + "loss": 3.4115, + "step": 2028544 + }, + { + "epoch": 1.01, + "learning_rate": 1.6780968878307453e-05, + "loss": 3.4006, + "step": 2029056 + }, + { + "epoch": 1.01, + "learning_rate": 1.6772582930796933e-05, + "loss": 3.4039, + "step": 2029568 + }, + { + "epoch": 1.01, + "learning_rate": 1.6764196983286413e-05, + "loss": 3.3982, + "step": 2030080 + }, + { + "epoch": 1.02, + "learning_rate": 1.6755827414579626e-05, + "loss": 3.3944, + "step": 2030592 + }, + { + "epoch": 1.02, + "learning_rate": 1.6747441467069106e-05, + "loss": 3.3995, + "step": 2031104 + }, + { + "epoch": 1.02, + "learning_rate": 1.6739055519558586e-05, + "loss": 3.3923, + "step": 2031616 + }, + { + "epoch": 1.02, + "learning_rate": 1.6730669572048066e-05, + "loss": 3.4082, + "step": 2032128 + }, + { + "epoch": 1.02, + "learning_rate": 1.6722300003341275e-05, + "loss": 3.4182, + "step": 2032640 + }, + { + "epoch": 1.02, + "learning_rate": 1.6713914055830758e-05, + "loss": 3.4118, + "step": 2033152 + }, + { + "epoch": 1.02, + "learning_rate": 1.6705528108320238e-05, + "loss": 3.394, + "step": 2033664 + }, + { + "epoch": 1.02, + "learning_rate": 1.6697142160809718e-05, + "loss": 3.3974, + "step": 2034176 + }, + { + "epoch": 1.02, + "learning_rate": 1.6688772592102927e-05, + "loss": 3.3998, + "step": 2034688 + }, + { + "epoch": 1.02, + "learning_rate": 1.6680386644592407e-05, + "loss": 3.4029, + "step": 2035200 + }, + { + "epoch": 1.02, + "learning_rate": 1.6672000697081887e-05, + "loss": 3.4051, + "step": 2035712 + }, + { + "epoch": 1.02, + "learning_rate": 1.6663614749571367e-05, + "loss": 3.4057, + "step": 2036224 + }, + { + "epoch": 1.02, + "learning_rate": 1.6655228802060847e-05, + "loss": 3.4046, + "step": 2036736 + }, + { + "epoch": 1.02, + "learning_rate": 1.6646842854550327e-05, + "loss": 3.3958, + "step": 2037248 + }, + { + "epoch": 1.02, + "learning_rate": 1.6638456907039807e-05, + "loss": 3.4011, + "step": 2037760 + }, + { + "epoch": 1.02, + "learning_rate": 1.6630070959529287e-05, + "loss": 3.3939, + "step": 2038272 + }, + { + "epoch": 1.02, + "learning_rate": 1.6621701390822496e-05, + "loss": 3.3934, + "step": 2038784 + }, + { + "epoch": 1.02, + "learning_rate": 1.6613331822115712e-05, + "loss": 3.4041, + "step": 2039296 + }, + { + "epoch": 1.02, + "learning_rate": 1.6604945874605192e-05, + "loss": 3.4015, + "step": 2039808 + }, + { + "epoch": 1.02, + "learning_rate": 1.659655992709467e-05, + "loss": 3.3886, + "step": 2040320 + }, + { + "epoch": 1.02, + "learning_rate": 1.6588173979584148e-05, + "loss": 3.3974, + "step": 2040832 + }, + { + "epoch": 1.02, + "learning_rate": 1.6579788032073628e-05, + "loss": 3.3867, + "step": 2041344 + }, + { + "epoch": 1.02, + "learning_rate": 1.657141846336684e-05, + "loss": 3.4077, + "step": 2041856 + }, + { + "epoch": 1.02, + "learning_rate": 1.656303251585632e-05, + "loss": 3.4, + "step": 2042368 + }, + { + "epoch": 1.02, + "learning_rate": 1.65546465683458e-05, + "loss": 3.4097, + "step": 2042880 + }, + { + "epoch": 1.02, + "learning_rate": 1.654626062083528e-05, + "loss": 3.4094, + "step": 2043392 + }, + { + "epoch": 1.02, + "learning_rate": 1.653787467332476e-05, + "loss": 3.413, + "step": 2043904 + }, + { + "epoch": 1.02, + "learning_rate": 1.652948872581424e-05, + "loss": 3.3968, + "step": 2044416 + }, + { + "epoch": 1.02, + "learning_rate": 1.652111915710745e-05, + "loss": 3.3971, + "step": 2044928 + }, + { + "epoch": 1.02, + "learning_rate": 1.651273320959693e-05, + "loss": 3.3997, + "step": 2045440 + }, + { + "epoch": 1.02, + "learning_rate": 1.6504347262086413e-05, + "loss": 3.4028, + "step": 2045952 + }, + { + "epoch": 1.02, + "learning_rate": 1.6495961314575893e-05, + "loss": 3.393, + "step": 2046464 + }, + { + "epoch": 1.02, + "learning_rate": 1.6487575367065373e-05, + "loss": 3.3918, + "step": 2046976 + }, + { + "epoch": 1.02, + "learning_rate": 1.6479189419554853e-05, + "loss": 3.4033, + "step": 2047488 + }, + { + "epoch": 1.02, + "learning_rate": 1.6470819850848062e-05, + "loss": 3.3965, + "step": 2048000 + }, + { + "epoch": 1.02, + "learning_rate": 1.6462433903337542e-05, + "loss": 3.3954, + "step": 2048512 + }, + { + "epoch": 1.02, + "learning_rate": 1.6454047955827022e-05, + "loss": 3.3955, + "step": 2049024 + }, + { + "epoch": 1.02, + "learning_rate": 1.64456620083165e-05, + "loss": 3.4037, + "step": 2049536 + }, + { + "epoch": 1.02, + "learning_rate": 1.643727606080598e-05, + "loss": 3.3887, + "step": 2050048 + }, + { + "epoch": 1.02, + "learning_rate": 1.642889011329546e-05, + "loss": 3.4085, + "step": 2050560 + }, + { + "epoch": 1.02, + "learning_rate": 1.6420520544588674e-05, + "loss": 3.4033, + "step": 2051072 + }, + { + "epoch": 1.02, + "learning_rate": 1.641213459707815e-05, + "loss": 3.4157, + "step": 2051584 + }, + { + "epoch": 1.02, + "learning_rate": 1.6403748649567634e-05, + "loss": 3.3865, + "step": 2052096 + }, + { + "epoch": 1.02, + "learning_rate": 1.6395362702057114e-05, + "loss": 3.406, + "step": 2052608 + }, + { + "epoch": 1.02, + "learning_rate": 1.6386976754546594e-05, + "loss": 3.4041, + "step": 2053120 + }, + { + "epoch": 1.02, + "learning_rate": 1.6378607185839803e-05, + "loss": 3.4009, + "step": 2053632 + }, + { + "epoch": 1.02, + "learning_rate": 1.6370221238329283e-05, + "loss": 3.4027, + "step": 2054144 + }, + { + "epoch": 1.02, + "learning_rate": 1.6361835290818763e-05, + "loss": 3.3969, + "step": 2054656 + }, + { + "epoch": 1.02, + "learning_rate": 1.6353449343308243e-05, + "loss": 3.3988, + "step": 2055168 + }, + { + "epoch": 1.02, + "learning_rate": 1.6345063395797723e-05, + "loss": 3.414, + "step": 2055680 + }, + { + "epoch": 1.02, + "learning_rate": 1.6336677448287206e-05, + "loss": 3.3928, + "step": 2056192 + }, + { + "epoch": 1.02, + "learning_rate": 1.6328307879580415e-05, + "loss": 3.4025, + "step": 2056704 + }, + { + "epoch": 1.02, + "learning_rate": 1.6319921932069895e-05, + "loss": 3.4026, + "step": 2057216 + }, + { + "epoch": 1.02, + "learning_rate": 1.6311535984559375e-05, + "loss": 3.3978, + "step": 2057728 + }, + { + "epoch": 1.02, + "learning_rate": 1.6303150037048855e-05, + "loss": 3.3968, + "step": 2058240 + }, + { + "epoch": 1.02, + "learning_rate": 1.6294780468342068e-05, + "loss": 3.4023, + "step": 2058752 + }, + { + "epoch": 1.02, + "learning_rate": 1.6286394520831548e-05, + "loss": 3.4018, + "step": 2059264 + }, + { + "epoch": 1.02, + "learning_rate": 1.6278008573321028e-05, + "loss": 3.4004, + "step": 2059776 + }, + { + "epoch": 1.02, + "learning_rate": 1.6269622625810507e-05, + "loss": 3.3949, + "step": 2060288 + }, + { + "epoch": 1.03, + "eval_loss": 3.8573341369628906, + "eval_runtime": 307.78, + "eval_samples_per_second": 1239.818, + "eval_steps_per_second": 38.745, + "step": 2060640 + }, + { + "epoch": 0.0, + "learning_rate": 1.6261236678299984e-05, + "loss": 3.3931, + "step": 2060800 + }, + { + "epoch": 0.0, + "learning_rate": 1.6252850730789464e-05, + "loss": 3.3901, + "step": 2061312 + }, + { + "epoch": 0.0, + "learning_rate": 1.6244481162082676e-05, + "loss": 3.3992, + "step": 2061824 + }, + { + "epoch": 0.0, + "learning_rate": 1.6236095214572156e-05, + "loss": 3.4043, + "step": 2062336 + }, + { + "epoch": 0.0, + "learning_rate": 1.6227709267061636e-05, + "loss": 3.4105, + "step": 2062848 + }, + { + "epoch": 0.0, + "learning_rate": 1.6219323319551116e-05, + "loss": 3.3994, + "step": 2063360 + }, + { + "epoch": 0.0, + "learning_rate": 1.621095375084433e-05, + "loss": 3.4003, + "step": 2063872 + }, + { + "epoch": 0.0, + "learning_rate": 1.6202567803333805e-05, + "loss": 3.3956, + "step": 2064384 + }, + { + "epoch": 0.0, + "learning_rate": 1.619418185582329e-05, + "loss": 3.3885, + "step": 2064896 + }, + { + "epoch": 0.0, + "learning_rate": 1.618579590831277e-05, + "loss": 3.4022, + "step": 2065408 + }, + { + "epoch": 0.0, + "learning_rate": 1.617740996080225e-05, + "loss": 3.3954, + "step": 2065920 + }, + { + "epoch": 0.0, + "learning_rate": 1.616902401329173e-05, + "loss": 3.404, + "step": 2066432 + }, + { + "epoch": 0.0, + "learning_rate": 1.6160654444584938e-05, + "loss": 3.4018, + "step": 2066944 + }, + { + "epoch": 0.0, + "learning_rate": 1.6152268497074418e-05, + "loss": 3.3884, + "step": 2067456 + }, + { + "epoch": 0.0, + "learning_rate": 1.6143882549563898e-05, + "loss": 3.3882, + "step": 2067968 + }, + { + "epoch": 0.0, + "learning_rate": 1.613549660205338e-05, + "loss": 3.3858, + "step": 2068480 + }, + { + "epoch": 0.0, + "learning_rate": 1.612711065454286e-05, + "loss": 3.3953, + "step": 2068992 + }, + { + "epoch": 0.0, + "learning_rate": 1.6118724707032337e-05, + "loss": 3.3935, + "step": 2069504 + }, + { + "epoch": 0.0, + "learning_rate": 1.6110338759521817e-05, + "loss": 3.391, + "step": 2070016 + }, + { + "epoch": 0.0, + "learning_rate": 1.6101952812011297e-05, + "loss": 3.398, + "step": 2070528 + }, + { + "epoch": 0.0, + "learning_rate": 1.609358324330451e-05, + "loss": 3.4017, + "step": 2071040 + }, + { + "epoch": 0.0, + "learning_rate": 1.6085213674597722e-05, + "loss": 3.4046, + "step": 2071552 + }, + { + "epoch": 0.0, + "learning_rate": 1.6076827727087202e-05, + "loss": 3.3964, + "step": 2072064 + }, + { + "epoch": 0.0, + "learning_rate": 1.6068441779576682e-05, + "loss": 3.3944, + "step": 2072576 + }, + { + "epoch": 0.0, + "learning_rate": 1.606005583206616e-05, + "loss": 3.3994, + "step": 2073088 + }, + { + "epoch": 0.0, + "learning_rate": 1.605166988455564e-05, + "loss": 3.4006, + "step": 2073600 + }, + { + "epoch": 0.0, + "learning_rate": 1.604328393704512e-05, + "loss": 3.3875, + "step": 2074112 + }, + { + "epoch": 0.0, + "learning_rate": 1.6034914368338335e-05, + "loss": 3.3951, + "step": 2074624 + }, + { + "epoch": 0.0, + "learning_rate": 1.602652842082781e-05, + "loss": 3.3892, + "step": 2075136 + }, + { + "epoch": 0.0, + "learning_rate": 1.601814247331729e-05, + "loss": 3.386, + "step": 2075648 + }, + { + "epoch": 0.01, + "learning_rate": 1.600975652580677e-05, + "loss": 3.3893, + "step": 2076160 + }, + { + "epoch": 0.01, + "learning_rate": 1.600137057829625e-05, + "loss": 3.3973, + "step": 2076672 + }, + { + "epoch": 0.01, + "learning_rate": 1.599298463078573e-05, + "loss": 3.3977, + "step": 2077184 + }, + { + "epoch": 0.01, + "learning_rate": 1.598459868327521e-05, + "loss": 3.4089, + "step": 2077696 + }, + { + "epoch": 0.01, + "learning_rate": 1.597621273576469e-05, + "loss": 3.3888, + "step": 2078208 + }, + { + "epoch": 0.01, + "learning_rate": 1.5967843167057903e-05, + "loss": 3.3948, + "step": 2078720 + }, + { + "epoch": 0.01, + "learning_rate": 1.5959473598351113e-05, + "loss": 3.4095, + "step": 2079232 + }, + { + "epoch": 0.01, + "learning_rate": 1.5951087650840592e-05, + "loss": 3.3876, + "step": 2079744 + }, + { + "epoch": 0.01, + "learning_rate": 1.5942701703330072e-05, + "loss": 3.3873, + "step": 2080256 + }, + { + "epoch": 0.01, + "learning_rate": 1.5934315755819552e-05, + "loss": 3.3847, + "step": 2080768 + }, + { + "epoch": 0.01, + "learning_rate": 1.5925929808309036e-05, + "loss": 3.3946, + "step": 2081280 + }, + { + "epoch": 0.01, + "learning_rate": 1.5917560239602245e-05, + "loss": 3.3925, + "step": 2081792 + }, + { + "epoch": 0.01, + "learning_rate": 1.5909174292091725e-05, + "loss": 3.3949, + "step": 2082304 + }, + { + "epoch": 0.01, + "learning_rate": 1.5900788344581205e-05, + "loss": 3.394, + "step": 2082816 + }, + { + "epoch": 0.01, + "learning_rate": 1.5892402397070685e-05, + "loss": 3.3956, + "step": 2083328 + }, + { + "epoch": 0.01, + "learning_rate": 1.5884016449560165e-05, + "loss": 3.4005, + "step": 2083840 + }, + { + "epoch": 0.01, + "learning_rate": 1.5875630502049645e-05, + "loss": 3.3864, + "step": 2084352 + }, + { + "epoch": 0.01, + "learning_rate": 1.5867244554539125e-05, + "loss": 3.3885, + "step": 2084864 + }, + { + "epoch": 0.01, + "learning_rate": 1.5858874985832337e-05, + "loss": 3.3641, + "step": 2085376 + }, + { + "epoch": 0.01, + "learning_rate": 1.5850489038321814e-05, + "loss": 3.4049, + "step": 2085888 + }, + { + "epoch": 0.01, + "learning_rate": 1.5842103090811294e-05, + "loss": 3.3876, + "step": 2086400 + }, + { + "epoch": 0.01, + "learning_rate": 1.5833717143300774e-05, + "loss": 3.3967, + "step": 2086912 + }, + { + "epoch": 0.01, + "learning_rate": 1.5825331195790253e-05, + "loss": 3.3911, + "step": 2087424 + }, + { + "epoch": 0.01, + "learning_rate": 1.5816961627083466e-05, + "loss": 3.3865, + "step": 2087936 + }, + { + "epoch": 0.01, + "learning_rate": 1.5808575679572946e-05, + "loss": 3.3767, + "step": 2088448 + }, + { + "epoch": 0.01, + "learning_rate": 1.5800189732062426e-05, + "loss": 3.3891, + "step": 2088960 + }, + { + "epoch": 0.01, + "learning_rate": 1.5791803784551906e-05, + "loss": 3.3942, + "step": 2089472 + }, + { + "epoch": 0.01, + "learning_rate": 1.5783417837041386e-05, + "loss": 3.3805, + "step": 2089984 + }, + { + "epoch": 0.01, + "learning_rate": 1.5775031889530866e-05, + "loss": 3.4007, + "step": 2090496 + }, + { + "epoch": 0.01, + "learning_rate": 1.5766662320824078e-05, + "loss": 3.3932, + "step": 2091008 + }, + { + "epoch": 0.01, + "learning_rate": 1.5758276373313558e-05, + "loss": 3.3723, + "step": 2091520 + }, + { + "epoch": 0.01, + "learning_rate": 1.5749890425803038e-05, + "loss": 3.3989, + "step": 2092032 + }, + { + "epoch": 0.01, + "learning_rate": 1.5741504478292518e-05, + "loss": 3.3888, + "step": 2092544 + }, + { + "epoch": 0.01, + "learning_rate": 1.5733118530781995e-05, + "loss": 3.3833, + "step": 2093056 + }, + { + "epoch": 0.01, + "learning_rate": 1.5724732583271475e-05, + "loss": 3.3921, + "step": 2093568 + }, + { + "epoch": 0.01, + "learning_rate": 1.571636301456469e-05, + "loss": 3.3934, + "step": 2094080 + }, + { + "epoch": 0.01, + "learning_rate": 1.570797706705417e-05, + "loss": 3.3795, + "step": 2094592 + }, + { + "epoch": 0.01, + "learning_rate": 1.5699591119543647e-05, + "loss": 3.3934, + "step": 2095104 + }, + { + "epoch": 0.01, + "learning_rate": 1.5691205172033127e-05, + "loss": 3.3791, + "step": 2095616 + }, + { + "epoch": 0.01, + "learning_rate": 1.568283560332634e-05, + "loss": 3.3792, + "step": 2096128 + }, + { + "epoch": 0.01, + "learning_rate": 1.567444965581582e-05, + "loss": 3.3959, + "step": 2096640 + }, + { + "epoch": 0.01, + "learning_rate": 1.56660637083053e-05, + "loss": 3.3872, + "step": 2097152 + }, + { + "epoch": 0.01, + "learning_rate": 1.565767776079478e-05, + "loss": 3.3984, + "step": 2097664 + }, + { + "epoch": 0.01, + "learning_rate": 1.564929181328426e-05, + "loss": 3.3931, + "step": 2098176 + }, + { + "epoch": 0.01, + "learning_rate": 1.564090586577374e-05, + "loss": 3.4043, + "step": 2098688 + }, + { + "epoch": 0.01, + "learning_rate": 1.563251991826322e-05, + "loss": 3.3887, + "step": 2099200 + }, + { + "epoch": 0.01, + "learning_rate": 1.56241339707527e-05, + "loss": 3.4053, + "step": 2099712 + }, + { + "epoch": 0.01, + "learning_rate": 1.5615764402045908e-05, + "loss": 3.3862, + "step": 2100224 + }, + { + "epoch": 0.01, + "learning_rate": 1.560737845453539e-05, + "loss": 3.39, + "step": 2100736 + }, + { + "epoch": 0.01, + "learning_rate": 1.559899250702487e-05, + "loss": 3.3884, + "step": 2101248 + }, + { + "epoch": 0.01, + "learning_rate": 1.559060655951435e-05, + "loss": 3.401, + "step": 2101760 + }, + { + "epoch": 0.01, + "learning_rate": 1.558223699080756e-05, + "loss": 3.3969, + "step": 2102272 + }, + { + "epoch": 0.01, + "learning_rate": 1.557385104329704e-05, + "loss": 3.404, + "step": 2102784 + }, + { + "epoch": 0.01, + "learning_rate": 1.556546509578652e-05, + "loss": 3.3779, + "step": 2103296 + }, + { + "epoch": 0.01, + "learning_rate": 1.5557079148276e-05, + "loss": 3.3765, + "step": 2103808 + }, + { + "epoch": 0.01, + "learning_rate": 1.554869320076548e-05, + "loss": 3.392, + "step": 2104320 + }, + { + "epoch": 0.01, + "learning_rate": 1.554030725325496e-05, + "loss": 3.4004, + "step": 2104832 + }, + { + "epoch": 0.01, + "learning_rate": 1.5531937684548173e-05, + "loss": 3.3884, + "step": 2105344 + }, + { + "epoch": 0.01, + "learning_rate": 1.552355173703765e-05, + "loss": 3.3961, + "step": 2105856 + }, + { + "epoch": 0.01, + "learning_rate": 1.551516578952713e-05, + "loss": 3.3872, + "step": 2106368 + }, + { + "epoch": 0.02, + "learning_rate": 1.5506779842016613e-05, + "loss": 3.382, + "step": 2106880 + }, + { + "epoch": 0.02, + "learning_rate": 1.5498393894506093e-05, + "loss": 3.3892, + "step": 2107392 + }, + { + "epoch": 0.02, + "learning_rate": 1.5490007946995573e-05, + "loss": 3.3854, + "step": 2107904 + }, + { + "epoch": 0.02, + "learning_rate": 1.5481621999485053e-05, + "loss": 3.3977, + "step": 2108416 + }, + { + "epoch": 0.02, + "learning_rate": 1.547325243077826e-05, + "loss": 3.4033, + "step": 2108928 + }, + { + "epoch": 0.02, + "learning_rate": 1.546486648326774e-05, + "loss": 3.405, + "step": 2109440 + }, + { + "epoch": 0.02, + "learning_rate": 1.545648053575722e-05, + "loss": 3.3792, + "step": 2109952 + }, + { + "epoch": 0.02, + "learning_rate": 1.54480945882467e-05, + "loss": 3.3911, + "step": 2110464 + }, + { + "epoch": 0.02, + "learning_rate": 1.543970864073618e-05, + "loss": 3.3897, + "step": 2110976 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431339072029394e-05, + "loss": 3.3964, + "step": 2111488 + }, + { + "epoch": 0.02, + "learning_rate": 1.5422953124518874e-05, + "loss": 3.3903, + "step": 2112000 + }, + { + "epoch": 0.02, + "learning_rate": 1.5414567177008354e-05, + "loss": 3.3977, + "step": 2112512 + }, + { + "epoch": 0.02, + "learning_rate": 1.540618122949783e-05, + "loss": 3.3913, + "step": 2113024 + }, + { + "epoch": 0.02, + "learning_rate": 1.5397795281987314e-05, + "loss": 3.3876, + "step": 2113536 + }, + { + "epoch": 0.02, + "learning_rate": 1.5389409334476794e-05, + "loss": 3.3901, + "step": 2114048 + }, + { + "epoch": 0.02, + "learning_rate": 1.5381023386966274e-05, + "loss": 3.3815, + "step": 2114560 + }, + { + "epoch": 0.02, + "learning_rate": 1.5372637439455754e-05, + "loss": 3.3839, + "step": 2115072 + }, + { + "epoch": 0.02, + "learning_rate": 1.5364267870748963e-05, + "loss": 3.3923, + "step": 2115584 + }, + { + "epoch": 0.02, + "learning_rate": 1.5355898302042175e-05, + "loss": 3.3945, + "step": 2116096 + }, + { + "epoch": 0.02, + "learning_rate": 1.5347512354531655e-05, + "loss": 3.38, + "step": 2116608 + }, + { + "epoch": 0.02, + "learning_rate": 1.5339126407021135e-05, + "loss": 3.3874, + "step": 2117120 + }, + { + "epoch": 0.02, + "learning_rate": 1.5330740459510615e-05, + "loss": 3.372, + "step": 2117632 + }, + { + "epoch": 0.02, + "learning_rate": 1.5322354512000095e-05, + "loss": 3.3985, + "step": 2118144 + }, + { + "epoch": 0.02, + "learning_rate": 1.5313984943293304e-05, + "loss": 3.3864, + "step": 2118656 + }, + { + "epoch": 0.02, + "learning_rate": 1.5305598995782784e-05, + "loss": 3.4003, + "step": 2119168 + }, + { + "epoch": 0.02, + "learning_rate": 1.5297213048272267e-05, + "loss": 3.3964, + "step": 2119680 + }, + { + "epoch": 0.02, + "learning_rate": 1.5288827100761747e-05, + "loss": 3.4023, + "step": 2120192 + }, + { + "epoch": 0.02, + "learning_rate": 1.5280441153251227e-05, + "loss": 3.3892, + "step": 2120704 + }, + { + "epoch": 0.02, + "learning_rate": 1.5272055205740707e-05, + "loss": 3.3861, + "step": 2121216 + }, + { + "epoch": 0.02, + "learning_rate": 1.5263685637033916e-05, + "loss": 3.3948, + "step": 2121728 + }, + { + "epoch": 0.02, + "learning_rate": 1.5255299689523398e-05, + "loss": 3.3904, + "step": 2122240 + }, + { + "epoch": 0.02, + "learning_rate": 1.5246913742012878e-05, + "loss": 3.3877, + "step": 2122752 + }, + { + "epoch": 0.02, + "learning_rate": 1.5238527794502358e-05, + "loss": 3.3816, + "step": 2123264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5230141846991836e-05, + "loss": 3.3913, + "step": 2123776 + }, + { + "epoch": 0.02, + "learning_rate": 1.5221772278285049e-05, + "loss": 3.3868, + "step": 2124288 + }, + { + "epoch": 0.02, + "learning_rate": 1.5213386330774529e-05, + "loss": 3.3884, + "step": 2124800 + }, + { + "epoch": 0.02, + "learning_rate": 1.5205000383264009e-05, + "loss": 3.3828, + "step": 2125312 + }, + { + "epoch": 0.02, + "learning_rate": 1.5196614435753487e-05, + "loss": 3.392, + "step": 2125824 + }, + { + "epoch": 0.02, + "learning_rate": 1.5188228488242967e-05, + "loss": 3.378, + "step": 2126336 + }, + { + "epoch": 0.02, + "learning_rate": 1.5179842540732447e-05, + "loss": 3.3983, + "step": 2126848 + }, + { + "epoch": 0.02, + "learning_rate": 1.5171472972025661e-05, + "loss": 3.3894, + "step": 2127360 + }, + { + "epoch": 0.02, + "learning_rate": 1.5163087024515138e-05, + "loss": 3.4073, + "step": 2127872 + }, + { + "epoch": 0.02, + "learning_rate": 1.5154701077004618e-05, + "loss": 3.3799, + "step": 2128384 + }, + { + "epoch": 0.02, + "learning_rate": 1.51463151294941e-05, + "loss": 3.396, + "step": 2128896 + }, + { + "epoch": 0.02, + "learning_rate": 1.5137929181983579e-05, + "loss": 3.3894, + "step": 2129408 + }, + { + "epoch": 0.02, + "learning_rate": 1.512955961327679e-05, + "loss": 3.3903, + "step": 2129920 + }, + { + "epoch": 0.02, + "learning_rate": 1.512117366576627e-05, + "loss": 3.3941, + "step": 2130432 + }, + { + "epoch": 0.02, + "learning_rate": 1.511278771825575e-05, + "loss": 3.3849, + "step": 2130944 + }, + { + "epoch": 0.02, + "learning_rate": 1.510440177074523e-05, + "loss": 3.3917, + "step": 2131456 + }, + { + "epoch": 0.02, + "learning_rate": 1.509601582323471e-05, + "loss": 3.4012, + "step": 2131968 + }, + { + "epoch": 0.02, + "learning_rate": 1.5087629875724191e-05, + "loss": 3.3838, + "step": 2132480 + }, + { + "epoch": 0.02, + "learning_rate": 1.50792603070174e-05, + "loss": 3.3927, + "step": 2132992 + }, + { + "epoch": 0.02, + "learning_rate": 1.5070874359506882e-05, + "loss": 3.3911, + "step": 2133504 + }, + { + "epoch": 0.02, + "learning_rate": 1.5062488411996362e-05, + "loss": 3.3874, + "step": 2134016 + }, + { + "epoch": 0.02, + "learning_rate": 1.5054102464485842e-05, + "loss": 3.3877, + "step": 2134528 + }, + { + "epoch": 0.02, + "learning_rate": 1.5045732895779053e-05, + "loss": 3.3883, + "step": 2135040 + }, + { + "epoch": 0.02, + "learning_rate": 1.5037346948268533e-05, + "loss": 3.3919, + "step": 2135552 + }, + { + "epoch": 0.02, + "learning_rate": 1.5028961000758013e-05, + "loss": 3.388, + "step": 2136064 + }, + { + "epoch": 0.02, + "learning_rate": 1.5020575053247491e-05, + "loss": 3.3833, + "step": 2136576 + }, + { + "epoch": 0.03, + "eval_loss": 3.8597192764282227, + "eval_runtime": 302.2875, + "eval_samples_per_second": 1262.345, + "eval_steps_per_second": 39.449, + "step": 2136960 + }, + { + "epoch": 1.0, + "learning_rate": 1.5012189105736971e-05, + "loss": 3.39, + "step": 2137088 + }, + { + "epoch": 1.0, + "learning_rate": 1.5003819537030183e-05, + "loss": 3.3769, + "step": 2137600 + }, + { + "epoch": 1.0, + "learning_rate": 1.4995433589519663e-05, + "loss": 3.3876, + "step": 2138112 + }, + { + "epoch": 1.0, + "learning_rate": 1.4987047642009142e-05, + "loss": 3.3974, + "step": 2138624 + }, + { + "epoch": 1.0, + "learning_rate": 1.4978661694498622e-05, + "loss": 3.3973, + "step": 2139136 + }, + { + "epoch": 1.0, + "learning_rate": 1.4970292125791834e-05, + "loss": 3.3919, + "step": 2139648 + }, + { + "epoch": 1.0, + "learning_rate": 1.4961906178281316e-05, + "loss": 3.392, + "step": 2140160 + }, + { + "epoch": 1.0, + "learning_rate": 1.4953520230770792e-05, + "loss": 3.3865, + "step": 2140672 + }, + { + "epoch": 1.0, + "learning_rate": 1.4945134283260272e-05, + "loss": 3.3795, + "step": 2141184 + }, + { + "epoch": 1.0, + "learning_rate": 1.4936748335749754e-05, + "loss": 3.3881, + "step": 2141696 + }, + { + "epoch": 1.0, + "learning_rate": 1.4928362388239234e-05, + "loss": 3.3883, + "step": 2142208 + }, + { + "epoch": 1.0, + "learning_rate": 1.4919976440728714e-05, + "loss": 3.391, + "step": 2142720 + }, + { + "epoch": 1.0, + "learning_rate": 1.4911606872021925e-05, + "loss": 3.394, + "step": 2143232 + }, + { + "epoch": 1.0, + "learning_rate": 1.4903220924511405e-05, + "loss": 3.3773, + "step": 2143744 + }, + { + "epoch": 1.0, + "learning_rate": 1.4894834977000885e-05, + "loss": 3.3816, + "step": 2144256 + }, + { + "epoch": 1.0, + "learning_rate": 1.4886449029490364e-05, + "loss": 3.3771, + "step": 2144768 + }, + { + "epoch": 1.0, + "learning_rate": 1.4878063081979846e-05, + "loss": 3.3854, + "step": 2145280 + }, + { + "epoch": 1.0, + "learning_rate": 1.4869677134469323e-05, + "loss": 3.3837, + "step": 2145792 + }, + { + "epoch": 1.0, + "learning_rate": 1.4861291186958803e-05, + "loss": 3.3816, + "step": 2146304 + }, + { + "epoch": 1.0, + "learning_rate": 1.4852905239448284e-05, + "loss": 3.3893, + "step": 2146816 + }, + { + "epoch": 1.0, + "learning_rate": 1.4844535670741493e-05, + "loss": 3.3919, + "step": 2147328 + }, + { + "epoch": 1.0, + "learning_rate": 1.4836149723230975e-05, + "loss": 3.3942, + "step": 2147840 + }, + { + "epoch": 1.0, + "learning_rate": 1.4827780154524188e-05, + "loss": 3.3888, + "step": 2148352 + }, + { + "epoch": 1.0, + "learning_rate": 1.4819394207013668e-05, + "loss": 3.3828, + "step": 2148864 + }, + { + "epoch": 1.0, + "learning_rate": 1.4811008259503146e-05, + "loss": 3.3911, + "step": 2149376 + }, + { + "epoch": 1.0, + "learning_rate": 1.4802622311992626e-05, + "loss": 3.3909, + "step": 2149888 + }, + { + "epoch": 1.0, + "learning_rate": 1.4794236364482106e-05, + "loss": 3.3799, + "step": 2150400 + }, + { + "epoch": 1.0, + "learning_rate": 1.4785866795775318e-05, + "loss": 3.385, + "step": 2150912 + }, + { + "epoch": 1.0, + "learning_rate": 1.4777480848264796e-05, + "loss": 3.3783, + "step": 2151424 + }, + { + "epoch": 1.0, + "learning_rate": 1.4769094900754276e-05, + "loss": 3.3746, + "step": 2151936 + }, + { + "epoch": 1.01, + "learning_rate": 1.4760708953243756e-05, + "loss": 3.3819, + "step": 2152448 + }, + { + "epoch": 1.01, + "learning_rate": 1.4752323005733238e-05, + "loss": 3.3829, + "step": 2152960 + }, + { + "epoch": 1.01, + "learning_rate": 1.4743937058222718e-05, + "loss": 3.389, + "step": 2153472 + }, + { + "epoch": 1.01, + "learning_rate": 1.4735551110712198e-05, + "loss": 3.398, + "step": 2153984 + }, + { + "epoch": 1.01, + "learning_rate": 1.4727181542005409e-05, + "loss": 3.3815, + "step": 2154496 + }, + { + "epoch": 1.01, + "learning_rate": 1.4718795594494889e-05, + "loss": 3.3859, + "step": 2155008 + }, + { + "epoch": 1.01, + "learning_rate": 1.4710409646984369e-05, + "loss": 3.399, + "step": 2155520 + }, + { + "epoch": 1.01, + "learning_rate": 1.4702023699473849e-05, + "loss": 3.3771, + "step": 2156032 + }, + { + "epoch": 1.01, + "learning_rate": 1.469365413076706e-05, + "loss": 3.3765, + "step": 2156544 + }, + { + "epoch": 1.01, + "learning_rate": 1.468526818325654e-05, + "loss": 3.38, + "step": 2157056 + }, + { + "epoch": 1.01, + "learning_rate": 1.467688223574602e-05, + "loss": 3.3828, + "step": 2157568 + }, + { + "epoch": 1.01, + "learning_rate": 1.4668496288235501e-05, + "loss": 3.3821, + "step": 2158080 + }, + { + "epoch": 1.01, + "learning_rate": 1.4660110340724977e-05, + "loss": 3.387, + "step": 2158592 + }, + { + "epoch": 1.01, + "learning_rate": 1.4651724393214457e-05, + "loss": 3.3864, + "step": 2159104 + }, + { + "epoch": 1.01, + "learning_rate": 1.4643338445703939e-05, + "loss": 3.3819, + "step": 2159616 + }, + { + "epoch": 1.01, + "learning_rate": 1.4634952498193419e-05, + "loss": 3.3894, + "step": 2160128 + }, + { + "epoch": 1.01, + "learning_rate": 1.462658292948663e-05, + "loss": 3.3782, + "step": 2160640 + }, + { + "epoch": 1.01, + "learning_rate": 1.461819698197611e-05, + "loss": 3.3789, + "step": 2161152 + }, + { + "epoch": 1.01, + "learning_rate": 1.4609827413269322e-05, + "loss": 3.3539, + "step": 2161664 + }, + { + "epoch": 1.01, + "learning_rate": 1.46014414657588e-05, + "loss": 3.3935, + "step": 2162176 + }, + { + "epoch": 1.01, + "learning_rate": 1.459305551824828e-05, + "loss": 3.3775, + "step": 2162688 + }, + { + "epoch": 1.01, + "learning_rate": 1.458466957073776e-05, + "loss": 3.3866, + "step": 2163200 + }, + { + "epoch": 1.01, + "learning_rate": 1.457628362322724e-05, + "loss": 3.3798, + "step": 2163712 + }, + { + "epoch": 1.01, + "learning_rate": 1.4567914054520451e-05, + "loss": 3.3775, + "step": 2164224 + }, + { + "epoch": 1.01, + "learning_rate": 1.4559528107009931e-05, + "loss": 3.3666, + "step": 2164736 + }, + { + "epoch": 1.01, + "learning_rate": 1.4551142159499411e-05, + "loss": 3.3773, + "step": 2165248 + }, + { + "epoch": 1.01, + "learning_rate": 1.4542756211988893e-05, + "loss": 3.3866, + "step": 2165760 + }, + { + "epoch": 1.01, + "learning_rate": 1.4534370264478373e-05, + "loss": 3.3693, + "step": 2166272 + }, + { + "epoch": 1.01, + "learning_rate": 1.4525984316967853e-05, + "loss": 3.3925, + "step": 2166784 + }, + { + "epoch": 1.01, + "learning_rate": 1.4517614748261063e-05, + "loss": 3.3822, + "step": 2167296 + }, + { + "epoch": 1.01, + "learning_rate": 1.4509228800750543e-05, + "loss": 3.3653, + "step": 2167808 + }, + { + "epoch": 1.01, + "learning_rate": 1.4500842853240023e-05, + "loss": 3.3866, + "step": 2168320 + }, + { + "epoch": 1.01, + "learning_rate": 1.4492456905729503e-05, + "loss": 3.3752, + "step": 2168832 + }, + { + "epoch": 1.01, + "learning_rate": 1.4484070958218982e-05, + "loss": 3.3783, + "step": 2169344 + }, + { + "epoch": 1.01, + "learning_rate": 1.4475685010708462e-05, + "loss": 3.3803, + "step": 2169856 + }, + { + "epoch": 1.01, + "learning_rate": 1.4467315442001676e-05, + "loss": 3.3832, + "step": 2170368 + }, + { + "epoch": 1.01, + "learning_rate": 1.4458929494491156e-05, + "loss": 3.3728, + "step": 2170880 + }, + { + "epoch": 1.01, + "learning_rate": 1.4450543546980632e-05, + "loss": 3.3854, + "step": 2171392 + }, + { + "epoch": 1.01, + "learning_rate": 1.4442157599470114e-05, + "loss": 3.3674, + "step": 2171904 + }, + { + "epoch": 1.01, + "learning_rate": 1.4433788030763326e-05, + "loss": 3.3695, + "step": 2172416 + }, + { + "epoch": 1.01, + "learning_rate": 1.4425402083252803e-05, + "loss": 3.3829, + "step": 2172928 + }, + { + "epoch": 1.01, + "learning_rate": 1.4417016135742285e-05, + "loss": 3.3824, + "step": 2173440 + }, + { + "epoch": 1.01, + "learning_rate": 1.4408630188231765e-05, + "loss": 3.3851, + "step": 2173952 + }, + { + "epoch": 1.01, + "learning_rate": 1.4400244240721244e-05, + "loss": 3.3798, + "step": 2174464 + }, + { + "epoch": 1.01, + "learning_rate": 1.4391858293210724e-05, + "loss": 3.3986, + "step": 2174976 + }, + { + "epoch": 1.01, + "learning_rate": 1.4383472345700204e-05, + "loss": 3.3785, + "step": 2175488 + }, + { + "epoch": 1.01, + "learning_rate": 1.4375086398189686e-05, + "loss": 3.3947, + "step": 2176000 + }, + { + "epoch": 1.01, + "learning_rate": 1.4366716829482895e-05, + "loss": 3.376, + "step": 2176512 + }, + { + "epoch": 1.01, + "learning_rate": 1.4358330881972377e-05, + "loss": 3.3832, + "step": 2177024 + }, + { + "epoch": 1.01, + "learning_rate": 1.4349944934461857e-05, + "loss": 3.3758, + "step": 2177536 + }, + { + "epoch": 1.01, + "learning_rate": 1.4341558986951337e-05, + "loss": 3.3898, + "step": 2178048 + }, + { + "epoch": 1.01, + "learning_rate": 1.4333173039440815e-05, + "loss": 3.3862, + "step": 2178560 + }, + { + "epoch": 1.01, + "learning_rate": 1.4324787091930295e-05, + "loss": 3.3931, + "step": 2179072 + }, + { + "epoch": 1.01, + "learning_rate": 1.4316417523223507e-05, + "loss": 3.3731, + "step": 2179584 + }, + { + "epoch": 1.01, + "learning_rate": 1.4308031575712986e-05, + "loss": 3.3674, + "step": 2180096 + }, + { + "epoch": 1.01, + "learning_rate": 1.4299645628202466e-05, + "loss": 3.3782, + "step": 2180608 + }, + { + "epoch": 1.01, + "learning_rate": 1.4291259680691946e-05, + "loss": 3.388, + "step": 2181120 + }, + { + "epoch": 1.01, + "learning_rate": 1.4282873733181426e-05, + "loss": 3.3798, + "step": 2181632 + }, + { + "epoch": 1.01, + "learning_rate": 1.4274487785670907e-05, + "loss": 3.3848, + "step": 2182144 + }, + { + "epoch": 1.01, + "learning_rate": 1.4266101838160387e-05, + "loss": 3.3791, + "step": 2182656 + }, + { + "epoch": 1.02, + "learning_rate": 1.4257715890649867e-05, + "loss": 3.372, + "step": 2183168 + }, + { + "epoch": 1.02, + "learning_rate": 1.4249346321943078e-05, + "loss": 3.3798, + "step": 2183680 + }, + { + "epoch": 1.02, + "learning_rate": 1.4240976753236287e-05, + "loss": 3.3733, + "step": 2184192 + }, + { + "epoch": 1.02, + "learning_rate": 1.4232590805725769e-05, + "loss": 3.3874, + "step": 2184704 + }, + { + "epoch": 1.02, + "learning_rate": 1.4224204858215249e-05, + "loss": 3.3967, + "step": 2185216 + }, + { + "epoch": 1.02, + "learning_rate": 1.4215818910704729e-05, + "loss": 3.3942, + "step": 2185728 + }, + { + "epoch": 1.02, + "learning_rate": 1.4207432963194209e-05, + "loss": 3.3701, + "step": 2186240 + }, + { + "epoch": 1.02, + "learning_rate": 1.4199047015683688e-05, + "loss": 3.3801, + "step": 2186752 + }, + { + "epoch": 1.02, + "learning_rate": 1.4190661068173167e-05, + "loss": 3.382, + "step": 2187264 + }, + { + "epoch": 1.02, + "learning_rate": 1.418229149946638e-05, + "loss": 3.3838, + "step": 2187776 + }, + { + "epoch": 1.02, + "learning_rate": 1.417390555195586e-05, + "loss": 3.3822, + "step": 2188288 + }, + { + "epoch": 1.02, + "learning_rate": 1.416551960444534e-05, + "loss": 3.3862, + "step": 2188800 + }, + { + "epoch": 1.02, + "learning_rate": 1.4157133656934817e-05, + "loss": 3.3814, + "step": 2189312 + }, + { + "epoch": 1.02, + "learning_rate": 1.4148747709424297e-05, + "loss": 3.3769, + "step": 2189824 + }, + { + "epoch": 1.02, + "learning_rate": 1.4140361761913779e-05, + "loss": 3.3854, + "step": 2190336 + }, + { + "epoch": 1.02, + "learning_rate": 1.4131975814403259e-05, + "loss": 3.3698, + "step": 2190848 + }, + { + "epoch": 1.02, + "learning_rate": 1.412360624569647e-05, + "loss": 3.374, + "step": 2191360 + }, + { + "epoch": 1.02, + "learning_rate": 1.411522029818595e-05, + "loss": 3.3808, + "step": 2191872 + }, + { + "epoch": 1.02, + "learning_rate": 1.410683435067543e-05, + "loss": 3.3835, + "step": 2192384 + }, + { + "epoch": 1.02, + "learning_rate": 1.409844840316491e-05, + "loss": 3.3714, + "step": 2192896 + }, + { + "epoch": 1.02, + "learning_rate": 1.409006245565439e-05, + "loss": 3.3834, + "step": 2193408 + }, + { + "epoch": 1.02, + "learning_rate": 1.4081676508143871e-05, + "loss": 3.3604, + "step": 2193920 + }, + { + "epoch": 1.02, + "learning_rate": 1.407330693943708e-05, + "loss": 3.3869, + "step": 2194432 + }, + { + "epoch": 1.02, + "learning_rate": 1.4064920991926562e-05, + "loss": 3.3825, + "step": 2194944 + }, + { + "epoch": 1.02, + "learning_rate": 1.4056535044416042e-05, + "loss": 3.3839, + "step": 2195456 + }, + { + "epoch": 1.02, + "learning_rate": 1.4048149096905522e-05, + "loss": 3.3903, + "step": 2195968 + }, + { + "epoch": 1.02, + "learning_rate": 1.4039763149395e-05, + "loss": 3.3949, + "step": 2196480 + }, + { + "epoch": 1.02, + "learning_rate": 1.403137720188448e-05, + "loss": 3.3784, + "step": 2196992 + }, + { + "epoch": 1.02, + "learning_rate": 1.402299125437396e-05, + "loss": 3.379, + "step": 2197504 + }, + { + "epoch": 1.02, + "learning_rate": 1.401462168566717e-05, + "loss": 3.3828, + "step": 2198016 + }, + { + "epoch": 1.02, + "learning_rate": 1.400623573815665e-05, + "loss": 3.38, + "step": 2198528 + }, + { + "epoch": 1.02, + "learning_rate": 1.399784979064613e-05, + "loss": 3.3761, + "step": 2199040 + }, + { + "epoch": 1.02, + "learning_rate": 1.398946384313561e-05, + "loss": 3.3759, + "step": 2199552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3981077895625092e-05, + "loss": 3.3792, + "step": 2200064 + }, + { + "epoch": 1.02, + "learning_rate": 1.3972708326918301e-05, + "loss": 3.3794, + "step": 2200576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3964322379407781e-05, + "loss": 3.3767, + "step": 2201088 + }, + { + "epoch": 1.02, + "learning_rate": 1.3955936431897263e-05, + "loss": 3.3759, + "step": 2201600 + }, + { + "epoch": 1.02, + "learning_rate": 1.3947550484386743e-05, + "loss": 3.3785, + "step": 2202112 + }, + { + "epoch": 1.02, + "learning_rate": 1.3939164536876223e-05, + "loss": 3.3695, + "step": 2202624 + }, + { + "epoch": 1.02, + "learning_rate": 1.3930794968169434e-05, + "loss": 3.3887, + "step": 2203136 + }, + { + "epoch": 1.02, + "learning_rate": 1.3922409020658914e-05, + "loss": 3.3808, + "step": 2203648 + }, + { + "epoch": 1.02, + "learning_rate": 1.3914023073148394e-05, + "loss": 3.399, + "step": 2204160 + }, + { + "epoch": 1.02, + "learning_rate": 1.3905637125637874e-05, + "loss": 3.3649, + "step": 2204672 + }, + { + "epoch": 1.02, + "learning_rate": 1.3897251178127352e-05, + "loss": 3.3873, + "step": 2205184 + }, + { + "epoch": 1.02, + "learning_rate": 1.3888865230616832e-05, + "loss": 3.3833, + "step": 2205696 + }, + { + "epoch": 1.02, + "learning_rate": 1.3880479283106312e-05, + "loss": 3.3767, + "step": 2206208 + }, + { + "epoch": 1.02, + "learning_rate": 1.3872109714399526e-05, + "loss": 3.3836, + "step": 2206720 + }, + { + "epoch": 1.02, + "learning_rate": 1.3863723766889003e-05, + "loss": 3.377, + "step": 2207232 + }, + { + "epoch": 1.02, + "learning_rate": 1.3855337819378482e-05, + "loss": 3.3852, + "step": 2207744 + }, + { + "epoch": 1.02, + "learning_rate": 1.3846951871867964e-05, + "loss": 3.3891, + "step": 2208256 + }, + { + "epoch": 1.02, + "learning_rate": 1.3838565924357444e-05, + "loss": 3.3727, + "step": 2208768 + }, + { + "epoch": 1.02, + "learning_rate": 1.3830196355650655e-05, + "loss": 3.3811, + "step": 2209280 + }, + { + "epoch": 1.02, + "learning_rate": 1.3821810408140135e-05, + "loss": 3.3833, + "step": 2209792 + }, + { + "epoch": 1.02, + "learning_rate": 1.3813424460629615e-05, + "loss": 3.3752, + "step": 2210304 + }, + { + "epoch": 1.02, + "learning_rate": 1.3805038513119095e-05, + "loss": 3.3762, + "step": 2210816 + }, + { + "epoch": 1.02, + "learning_rate": 1.3796652565608575e-05, + "loss": 3.3844, + "step": 2211328 + }, + { + "epoch": 1.02, + "learning_rate": 1.3788266618098056e-05, + "loss": 3.3775, + "step": 2211840 + }, + { + "epoch": 1.02, + "learning_rate": 1.3779880670587533e-05, + "loss": 3.3822, + "step": 2212352 + }, + { + "epoch": 1.02, + "learning_rate": 1.3771511101880747e-05, + "loss": 3.373, + "step": 2212864 + }, + { + "epoch": 1.03, + "eval_loss": 3.860154867172241, + "eval_runtime": 302.2963, + "eval_samples_per_second": 1262.308, + "eval_steps_per_second": 39.448, + "step": 2213280 + }, + { + "epoch": 0.0, + "learning_rate": 1.3763125154370227e-05, + "loss": 3.39, + "step": 2213376 + }, + { + "epoch": 0.0, + "learning_rate": 1.3754739206859707e-05, + "loss": 3.3656, + "step": 2213888 + }, + { + "epoch": 0.0, + "learning_rate": 1.3746369638152918e-05, + "loss": 3.378, + "step": 2214400 + }, + { + "epoch": 0.0, + "learning_rate": 1.3737983690642398e-05, + "loss": 3.3906, + "step": 2214912 + }, + { + "epoch": 0.0, + "learning_rate": 1.3729597743131878e-05, + "loss": 3.3842, + "step": 2215424 + }, + { + "epoch": 0.0, + "learning_rate": 1.3721211795621358e-05, + "loss": 3.3837, + "step": 2215936 + }, + { + "epoch": 0.0, + "learning_rate": 1.3712842226914568e-05, + "loss": 3.3814, + "step": 2216448 + }, + { + "epoch": 0.0, + "learning_rate": 1.3704456279404048e-05, + "loss": 3.3773, + "step": 2216960 + }, + { + "epoch": 0.0, + "learning_rate": 1.3696070331893528e-05, + "loss": 3.3666, + "step": 2217472 + }, + { + "epoch": 0.0, + "learning_rate": 1.3687684384383007e-05, + "loss": 3.3824, + "step": 2217984 + }, + { + "epoch": 0.0, + "learning_rate": 1.3679298436872487e-05, + "loss": 3.3749, + "step": 2218496 + }, + { + "epoch": 0.0, + "learning_rate": 1.3670912489361967e-05, + "loss": 3.3809, + "step": 2219008 + }, + { + "epoch": 0.0, + "learning_rate": 1.366254292065518e-05, + "loss": 3.3858, + "step": 2219520 + }, + { + "epoch": 0.0, + "learning_rate": 1.3654156973144657e-05, + "loss": 3.3687, + "step": 2220032 + }, + { + "epoch": 0.0, + "learning_rate": 1.3645771025634139e-05, + "loss": 3.3691, + "step": 2220544 + }, + { + "epoch": 0.0, + "learning_rate": 1.3637385078123619e-05, + "loss": 3.3673, + "step": 2221056 + }, + { + "epoch": 0.0, + "learning_rate": 1.3628999130613099e-05, + "loss": 3.376, + "step": 2221568 + }, + { + "epoch": 0.0, + "learning_rate": 1.3620613183102579e-05, + "loss": 3.3721, + "step": 2222080 + }, + { + "epoch": 0.0, + "learning_rate": 1.3612227235592059e-05, + "loss": 3.3695, + "step": 2222592 + }, + { + "epoch": 0.0, + "learning_rate": 1.3603841288081537e-05, + "loss": 3.3749, + "step": 2223104 + }, + { + "epoch": 0.0, + "learning_rate": 1.359547171937475e-05, + "loss": 3.3843, + "step": 2223616 + }, + { + "epoch": 0.0, + "learning_rate": 1.358708577186423e-05, + "loss": 3.3819, + "step": 2224128 + }, + { + "epoch": 0.0, + "learning_rate": 1.357871620315744e-05, + "loss": 3.379, + "step": 2224640 + }, + { + "epoch": 0.0, + "learning_rate": 1.357033025564692e-05, + "loss": 3.3744, + "step": 2225152 + }, + { + "epoch": 0.0, + "learning_rate": 1.3561944308136402e-05, + "loss": 3.3818, + "step": 2225664 + }, + { + "epoch": 0.0, + "learning_rate": 1.3553558360625882e-05, + "loss": 3.3773, + "step": 2226176 + }, + { + "epoch": 0.0, + "learning_rate": 1.3545188791919091e-05, + "loss": 3.3719, + "step": 2226688 + }, + { + "epoch": 0.0, + "learning_rate": 1.3536802844408573e-05, + "loss": 3.3771, + "step": 2227200 + }, + { + "epoch": 0.0, + "learning_rate": 1.3528416896898053e-05, + "loss": 3.3671, + "step": 2227712 + }, + { + "epoch": 0.0, + "learning_rate": 1.3520030949387532e-05, + "loss": 3.3643, + "step": 2228224 + }, + { + "epoch": 0.01, + "learning_rate": 1.351164500187701e-05, + "loss": 3.3709, + "step": 2228736 + }, + { + "epoch": 0.01, + "learning_rate": 1.350325905436649e-05, + "loss": 3.3731, + "step": 2229248 + }, + { + "epoch": 0.01, + "learning_rate": 1.349487310685597e-05, + "loss": 3.3837, + "step": 2229760 + }, + { + "epoch": 0.01, + "learning_rate": 1.348648715934545e-05, + "loss": 3.3853, + "step": 2230272 + }, + { + "epoch": 0.01, + "learning_rate": 1.3478117590638661e-05, + "loss": 3.3726, + "step": 2230784 + }, + { + "epoch": 0.01, + "learning_rate": 1.3469731643128141e-05, + "loss": 3.3795, + "step": 2231296 + }, + { + "epoch": 0.01, + "learning_rate": 1.3461345695617621e-05, + "loss": 3.388, + "step": 2231808 + }, + { + "epoch": 0.01, + "learning_rate": 1.3452959748107103e-05, + "loss": 3.3622, + "step": 2232320 + }, + { + "epoch": 0.01, + "learning_rate": 1.3444590179400312e-05, + "loss": 3.3694, + "step": 2232832 + }, + { + "epoch": 0.01, + "learning_rate": 1.3436204231889794e-05, + "loss": 3.3701, + "step": 2233344 + }, + { + "epoch": 0.01, + "learning_rate": 1.3427818284379274e-05, + "loss": 3.372, + "step": 2233856 + }, + { + "epoch": 0.01, + "learning_rate": 1.3419432336868754e-05, + "loss": 3.3721, + "step": 2234368 + }, + { + "epoch": 0.01, + "learning_rate": 1.3411046389358234e-05, + "loss": 3.3774, + "step": 2234880 + }, + { + "epoch": 0.01, + "learning_rate": 1.3402660441847714e-05, + "loss": 3.3774, + "step": 2235392 + }, + { + "epoch": 0.01, + "learning_rate": 1.3394274494337192e-05, + "loss": 3.3701, + "step": 2235904 + }, + { + "epoch": 0.01, + "learning_rate": 1.3385888546826672e-05, + "loss": 3.3773, + "step": 2236416 + }, + { + "epoch": 0.01, + "learning_rate": 1.3377518978119886e-05, + "loss": 3.3704, + "step": 2236928 + }, + { + "epoch": 0.01, + "learning_rate": 1.3369133030609366e-05, + "loss": 3.3677, + "step": 2237440 + }, + { + "epoch": 0.01, + "learning_rate": 1.3360747083098842e-05, + "loss": 3.3491, + "step": 2237952 + }, + { + "epoch": 0.01, + "learning_rate": 1.3352361135588322e-05, + "loss": 3.3831, + "step": 2238464 + }, + { + "epoch": 0.01, + "learning_rate": 1.3343991566881537e-05, + "loss": 3.3683, + "step": 2238976 + }, + { + "epoch": 0.01, + "learning_rate": 1.3335605619371017e-05, + "loss": 3.3762, + "step": 2239488 + }, + { + "epoch": 0.01, + "learning_rate": 1.3327219671860495e-05, + "loss": 3.3702, + "step": 2240000 + }, + { + "epoch": 0.01, + "learning_rate": 1.3318833724349975e-05, + "loss": 3.3632, + "step": 2240512 + }, + { + "epoch": 0.01, + "learning_rate": 1.3310447776839455e-05, + "loss": 3.3581, + "step": 2241024 + }, + { + "epoch": 0.01, + "learning_rate": 1.3302061829328935e-05, + "loss": 3.3695, + "step": 2241536 + }, + { + "epoch": 0.01, + "learning_rate": 1.3293692260622145e-05, + "loss": 3.3777, + "step": 2242048 + }, + { + "epoch": 0.01, + "learning_rate": 1.3285306313111625e-05, + "loss": 3.3594, + "step": 2242560 + }, + { + "epoch": 0.01, + "learning_rate": 1.3276920365601105e-05, + "loss": 3.3844, + "step": 2243072 + }, + { + "epoch": 0.01, + "learning_rate": 1.3268534418090587e-05, + "loss": 3.3732, + "step": 2243584 + }, + { + "epoch": 0.01, + "learning_rate": 1.3260164849383796e-05, + "loss": 3.3542, + "step": 2244096 + }, + { + "epoch": 0.01, + "learning_rate": 1.3251778901873276e-05, + "loss": 3.3776, + "step": 2244608 + }, + { + "epoch": 0.01, + "learning_rate": 1.3243392954362758e-05, + "loss": 3.3652, + "step": 2245120 + }, + { + "epoch": 0.01, + "learning_rate": 1.3235007006852238e-05, + "loss": 3.3702, + "step": 2245632 + }, + { + "epoch": 0.01, + "learning_rate": 1.3226621059341718e-05, + "loss": 3.3632, + "step": 2246144 + }, + { + "epoch": 0.01, + "learning_rate": 1.3218235111831198e-05, + "loss": 3.3785, + "step": 2246656 + }, + { + "epoch": 0.01, + "learning_rate": 1.3209849164320676e-05, + "loss": 3.3594, + "step": 2247168 + }, + { + "epoch": 0.01, + "learning_rate": 1.3201463216810156e-05, + "loss": 3.3756, + "step": 2247680 + }, + { + "epoch": 0.01, + "learning_rate": 1.3193093648103368e-05, + "loss": 3.356, + "step": 2248192 + }, + { + "epoch": 0.01, + "learning_rate": 1.3184724079396579e-05, + "loss": 3.3655, + "step": 2248704 + }, + { + "epoch": 0.01, + "learning_rate": 1.3176338131886059e-05, + "loss": 3.3703, + "step": 2249216 + }, + { + "epoch": 0.01, + "learning_rate": 1.316795218437554e-05, + "loss": 3.3771, + "step": 2249728 + }, + { + "epoch": 0.01, + "learning_rate": 1.315956623686502e-05, + "loss": 3.3725, + "step": 2250240 + }, + { + "epoch": 0.01, + "learning_rate": 1.3151180289354497e-05, + "loss": 3.3711, + "step": 2250752 + }, + { + "epoch": 0.01, + "learning_rate": 1.3142794341843979e-05, + "loss": 3.3887, + "step": 2251264 + }, + { + "epoch": 0.01, + "learning_rate": 1.3134408394333459e-05, + "loss": 3.3693, + "step": 2251776 + }, + { + "epoch": 0.01, + "learning_rate": 1.3126022446822939e-05, + "loss": 3.3828, + "step": 2252288 + }, + { + "epoch": 0.01, + "learning_rate": 1.311765287811615e-05, + "loss": 3.3705, + "step": 2252800 + }, + { + "epoch": 0.01, + "learning_rate": 1.310926693060563e-05, + "loss": 3.3725, + "step": 2253312 + }, + { + "epoch": 0.01, + "learning_rate": 1.310088098309511e-05, + "loss": 3.3711, + "step": 2253824 + }, + { + "epoch": 0.01, + "learning_rate": 1.309249503558459e-05, + "loss": 3.3749, + "step": 2254336 + }, + { + "epoch": 0.01, + "learning_rate": 1.30841254668778e-05, + "loss": 3.3775, + "step": 2254848 + }, + { + "epoch": 0.01, + "learning_rate": 1.307573951936728e-05, + "loss": 3.3796, + "step": 2255360 + }, + { + "epoch": 0.01, + "learning_rate": 1.306735357185676e-05, + "loss": 3.3681, + "step": 2255872 + }, + { + "epoch": 0.01, + "learning_rate": 1.3058967624346242e-05, + "loss": 3.3575, + "step": 2256384 + }, + { + "epoch": 0.01, + "learning_rate": 1.3050598055639451e-05, + "loss": 3.3681, + "step": 2256896 + }, + { + "epoch": 0.01, + "learning_rate": 1.3042212108128933e-05, + "loss": 3.3744, + "step": 2257408 + }, + { + "epoch": 0.01, + "learning_rate": 1.3033826160618412e-05, + "loss": 3.3716, + "step": 2257920 + }, + { + "epoch": 0.01, + "learning_rate": 1.3025440213107892e-05, + "loss": 3.3754, + "step": 2258432 + }, + { + "epoch": 0.01, + "learning_rate": 1.3017054265597372e-05, + "loss": 3.3707, + "step": 2258944 + }, + { + "epoch": 0.02, + "learning_rate": 1.300866831808685e-05, + "loss": 3.3602, + "step": 2259456 + }, + { + "epoch": 0.02, + "learning_rate": 1.300028237057633e-05, + "loss": 3.3699, + "step": 2259968 + }, + { + "epoch": 0.02, + "learning_rate": 1.299189642306581e-05, + "loss": 3.364, + "step": 2260480 + }, + { + "epoch": 0.02, + "learning_rate": 1.2983526854359023e-05, + "loss": 3.3811, + "step": 2260992 + }, + { + "epoch": 0.02, + "learning_rate": 1.2975157285652234e-05, + "loss": 3.3798, + "step": 2261504 + }, + { + "epoch": 0.02, + "learning_rate": 1.2966771338141714e-05, + "loss": 3.3835, + "step": 2262016 + }, + { + "epoch": 0.02, + "learning_rate": 1.2958385390631195e-05, + "loss": 3.3626, + "step": 2262528 + }, + { + "epoch": 0.02, + "learning_rate": 1.2949999443120675e-05, + "loss": 3.3729, + "step": 2263040 + }, + { + "epoch": 0.02, + "learning_rate": 1.2941613495610152e-05, + "loss": 3.3731, + "step": 2263552 + }, + { + "epoch": 0.02, + "learning_rate": 1.2933243926903366e-05, + "loss": 3.3713, + "step": 2264064 + }, + { + "epoch": 0.02, + "learning_rate": 1.2924857979392846e-05, + "loss": 3.3766, + "step": 2264576 + }, + { + "epoch": 0.02, + "learning_rate": 1.2916472031882323e-05, + "loss": 3.3722, + "step": 2265088 + }, + { + "epoch": 0.02, + "learning_rate": 1.2908086084371804e-05, + "loss": 3.3718, + "step": 2265600 + }, + { + "epoch": 0.02, + "learning_rate": 1.2899700136861284e-05, + "loss": 3.3674, + "step": 2266112 + }, + { + "epoch": 0.02, + "learning_rate": 1.2891314189350764e-05, + "loss": 3.3794, + "step": 2266624 + }, + { + "epoch": 0.02, + "learning_rate": 1.2882928241840244e-05, + "loss": 3.3567, + "step": 2267136 + }, + { + "epoch": 0.02, + "learning_rate": 1.2874558673133455e-05, + "loss": 3.363, + "step": 2267648 + }, + { + "epoch": 0.02, + "learning_rate": 1.2866189104426667e-05, + "loss": 3.3733, + "step": 2268160 + }, + { + "epoch": 0.02, + "learning_rate": 1.2857803156916149e-05, + "loss": 3.3749, + "step": 2268672 + }, + { + "epoch": 0.02, + "learning_rate": 1.2849417209405626e-05, + "loss": 3.3604, + "step": 2269184 + }, + { + "epoch": 0.02, + "learning_rate": 1.2841031261895106e-05, + "loss": 3.3734, + "step": 2269696 + }, + { + "epoch": 0.02, + "learning_rate": 1.2832645314384587e-05, + "loss": 3.353, + "step": 2270208 + }, + { + "epoch": 0.02, + "learning_rate": 1.2824275745677796e-05, + "loss": 3.3782, + "step": 2270720 + }, + { + "epoch": 0.02, + "learning_rate": 1.2815889798167276e-05, + "loss": 3.3657, + "step": 2271232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2807503850656758e-05, + "loss": 3.3733, + "step": 2271744 + }, + { + "epoch": 0.02, + "learning_rate": 1.2799117903146238e-05, + "loss": 3.3819, + "step": 2272256 + }, + { + "epoch": 0.02, + "learning_rate": 1.2790731955635718e-05, + "loss": 3.3821, + "step": 2272768 + }, + { + "epoch": 0.02, + "learning_rate": 1.2782346008125198e-05, + "loss": 3.3647, + "step": 2273280 + }, + { + "epoch": 0.02, + "learning_rate": 1.2773960060614678e-05, + "loss": 3.3705, + "step": 2273792 + }, + { + "epoch": 0.02, + "learning_rate": 1.2765590491907889e-05, + "loss": 3.3731, + "step": 2274304 + }, + { + "epoch": 0.02, + "learning_rate": 1.2757204544397369e-05, + "loss": 3.3667, + "step": 2274816 + }, + { + "epoch": 0.02, + "learning_rate": 1.274881859688685e-05, + "loss": 3.3699, + "step": 2275328 + }, + { + "epoch": 0.02, + "learning_rate": 1.274043264937633e-05, + "loss": 3.3615, + "step": 2275840 + }, + { + "epoch": 0.02, + "learning_rate": 1.2732046701865807e-05, + "loss": 3.3719, + "step": 2276352 + }, + { + "epoch": 0.02, + "learning_rate": 1.2723677133159021e-05, + "loss": 3.364, + "step": 2276864 + }, + { + "epoch": 0.02, + "learning_rate": 1.2715291185648501e-05, + "loss": 3.366, + "step": 2277376 + }, + { + "epoch": 0.02, + "learning_rate": 1.2706905238137979e-05, + "loss": 3.3708, + "step": 2277888 + }, + { + "epoch": 0.02, + "learning_rate": 1.2698519290627459e-05, + "loss": 3.369, + "step": 2278400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2690133343116939e-05, + "loss": 3.3604, + "step": 2278912 + }, + { + "epoch": 0.02, + "learning_rate": 1.2681763774410152e-05, + "loss": 3.3791, + "step": 2279424 + }, + { + "epoch": 0.02, + "learning_rate": 1.267337782689963e-05, + "loss": 3.372, + "step": 2279936 + }, + { + "epoch": 0.02, + "learning_rate": 1.266499187938911e-05, + "loss": 3.3867, + "step": 2280448 + }, + { + "epoch": 0.02, + "learning_rate": 1.265660593187859e-05, + "loss": 3.3616, + "step": 2280960 + }, + { + "epoch": 0.02, + "learning_rate": 1.264821998436807e-05, + "loss": 3.3749, + "step": 2281472 + }, + { + "epoch": 0.02, + "learning_rate": 1.2639834036857551e-05, + "loss": 3.3754, + "step": 2281984 + }, + { + "epoch": 0.02, + "learning_rate": 1.2631448089347031e-05, + "loss": 3.3698, + "step": 2282496 + }, + { + "epoch": 0.02, + "learning_rate": 1.2623078520640242e-05, + "loss": 3.3691, + "step": 2283008 + }, + { + "epoch": 0.02, + "learning_rate": 1.2614692573129722e-05, + "loss": 3.3695, + "step": 2283520 + }, + { + "epoch": 0.02, + "learning_rate": 1.2606306625619202e-05, + "loss": 3.3759, + "step": 2284032 + }, + { + "epoch": 0.02, + "learning_rate": 1.2597920678108682e-05, + "loss": 3.3777, + "step": 2284544 + }, + { + "epoch": 0.02, + "learning_rate": 1.258953473059816e-05, + "loss": 3.3668, + "step": 2285056 + }, + { + "epoch": 0.02, + "learning_rate": 1.2581165161891373e-05, + "loss": 3.3696, + "step": 2285568 + }, + { + "epoch": 0.02, + "learning_rate": 1.2572779214380853e-05, + "loss": 3.3743, + "step": 2286080 + }, + { + "epoch": 0.02, + "learning_rate": 1.2564393266870334e-05, + "loss": 3.3661, + "step": 2286592 + }, + { + "epoch": 0.02, + "learning_rate": 1.255600731935981e-05, + "loss": 3.3663, + "step": 2287104 + }, + { + "epoch": 0.02, + "learning_rate": 1.2547637750653023e-05, + "loss": 3.3762, + "step": 2287616 + }, + { + "epoch": 0.02, + "learning_rate": 1.2539251803142505e-05, + "loss": 3.3688, + "step": 2288128 + }, + { + "epoch": 0.02, + "learning_rate": 1.2530865855631985e-05, + "loss": 3.375, + "step": 2288640 + }, + { + "epoch": 0.02, + "learning_rate": 1.2522479908121461e-05, + "loss": 3.3626, + "step": 2289152 + }, + { + "epoch": 0.03, + "eval_loss": 3.861098289489746, + "eval_runtime": 312.3536, + "eval_samples_per_second": 1221.664, + "eval_steps_per_second": 38.178, + "step": 2289600 + }, + { + "epoch": 1.0, + "learning_rate": 1.2514093960610943e-05, + "loss": 3.3685, + "step": 2289664 + }, + { + "epoch": 1.0, + "learning_rate": 1.2505708013100423e-05, + "loss": 3.3586, + "step": 2290176 + }, + { + "epoch": 1.0, + "learning_rate": 1.2497338444393634e-05, + "loss": 3.3658, + "step": 2290688 + }, + { + "epoch": 1.0, + "learning_rate": 1.2488952496883116e-05, + "loss": 3.3796, + "step": 2291200 + }, + { + "epoch": 1.0, + "learning_rate": 1.2480566549372594e-05, + "loss": 3.377, + "step": 2291712 + }, + { + "epoch": 1.0, + "learning_rate": 1.2472180601862074e-05, + "loss": 3.3748, + "step": 2292224 + }, + { + "epoch": 1.0, + "learning_rate": 1.2463811033155286e-05, + "loss": 3.3662, + "step": 2292736 + }, + { + "epoch": 1.0, + "learning_rate": 1.2455425085644764e-05, + "loss": 3.3645, + "step": 2293248 + }, + { + "epoch": 1.0, + "learning_rate": 1.2447039138134244e-05, + "loss": 3.3582, + "step": 2293760 + }, + { + "epoch": 1.0, + "learning_rate": 1.2438653190623726e-05, + "loss": 3.3765, + "step": 2294272 + }, + { + "epoch": 1.0, + "learning_rate": 1.2430267243113206e-05, + "loss": 3.3645, + "step": 2294784 + }, + { + "epoch": 1.0, + "learning_rate": 1.2421881295602684e-05, + "loss": 3.3748, + "step": 2295296 + }, + { + "epoch": 1.0, + "learning_rate": 1.2413511726895897e-05, + "loss": 3.3711, + "step": 2295808 + }, + { + "epoch": 1.0, + "learning_rate": 1.2405125779385377e-05, + "loss": 3.3597, + "step": 2296320 + }, + { + "epoch": 1.0, + "learning_rate": 1.2396739831874855e-05, + "loss": 3.3602, + "step": 2296832 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388353884364335e-05, + "loss": 3.3568, + "step": 2297344 + }, + { + "epoch": 1.0, + "learning_rate": 1.2379967936853817e-05, + "loss": 3.3667, + "step": 2297856 + }, + { + "epoch": 1.0, + "learning_rate": 1.2371598368147027e-05, + "loss": 3.359, + "step": 2298368 + }, + { + "epoch": 1.0, + "learning_rate": 1.2363212420636507e-05, + "loss": 3.3659, + "step": 2298880 + }, + { + "epoch": 1.0, + "learning_rate": 1.2354826473125987e-05, + "loss": 3.3657, + "step": 2299392 + }, + { + "epoch": 1.0, + "learning_rate": 1.2346440525615467e-05, + "loss": 3.3739, + "step": 2299904 + }, + { + "epoch": 1.0, + "learning_rate": 1.2338054578104946e-05, + "loss": 3.3727, + "step": 2300416 + }, + { + "epoch": 1.0, + "learning_rate": 1.2329685009398158e-05, + "loss": 3.3688, + "step": 2300928 + }, + { + "epoch": 1.0, + "learning_rate": 1.2321299061887638e-05, + "loss": 3.3656, + "step": 2301440 + }, + { + "epoch": 1.0, + "learning_rate": 1.2312913114377118e-05, + "loss": 3.3738, + "step": 2301952 + }, + { + "epoch": 1.0, + "learning_rate": 1.2304527166866598e-05, + "loss": 3.3648, + "step": 2302464 + }, + { + "epoch": 1.0, + "learning_rate": 1.2296141219356078e-05, + "loss": 3.3601, + "step": 2302976 + }, + { + "epoch": 1.0, + "learning_rate": 1.2287755271845558e-05, + "loss": 3.3729, + "step": 2303488 + }, + { + "epoch": 1.0, + "learning_rate": 1.227938570313877e-05, + "loss": 3.354, + "step": 2304000 + }, + { + "epoch": 1.0, + "learning_rate": 1.2270999755628249e-05, + "loss": 3.3536, + "step": 2304512 + }, + { + "epoch": 1.01, + "learning_rate": 1.2262613808117729e-05, + "loss": 3.3605, + "step": 2305024 + }, + { + "epoch": 1.01, + "learning_rate": 1.2254227860607208e-05, + "loss": 3.3612, + "step": 2305536 + }, + { + "epoch": 1.01, + "learning_rate": 1.2245841913096688e-05, + "loss": 3.3751, + "step": 2306048 + }, + { + "epoch": 1.01, + "learning_rate": 1.2237455965586168e-05, + "loss": 3.3768, + "step": 2306560 + }, + { + "epoch": 1.01, + "learning_rate": 1.2229070018075648e-05, + "loss": 3.36, + "step": 2307072 + }, + { + "epoch": 1.01, + "learning_rate": 1.222070044936886e-05, + "loss": 3.3726, + "step": 2307584 + }, + { + "epoch": 1.01, + "learning_rate": 1.221233088066207e-05, + "loss": 3.3754, + "step": 2308096 + }, + { + "epoch": 1.01, + "learning_rate": 1.2203944933151552e-05, + "loss": 3.3554, + "step": 2308608 + }, + { + "epoch": 1.01, + "learning_rate": 1.2195558985641032e-05, + "loss": 3.3617, + "step": 2309120 + }, + { + "epoch": 1.01, + "learning_rate": 1.218717303813051e-05, + "loss": 3.3584, + "step": 2309632 + }, + { + "epoch": 1.01, + "learning_rate": 1.217878709061999e-05, + "loss": 3.3578, + "step": 2310144 + }, + { + "epoch": 1.01, + "learning_rate": 1.2170417521913202e-05, + "loss": 3.366, + "step": 2310656 + }, + { + "epoch": 1.01, + "learning_rate": 1.2162031574402682e-05, + "loss": 3.3705, + "step": 2311168 + }, + { + "epoch": 1.01, + "learning_rate": 1.2153645626892162e-05, + "loss": 3.3641, + "step": 2311680 + }, + { + "epoch": 1.01, + "learning_rate": 1.2145259679381642e-05, + "loss": 3.3616, + "step": 2312192 + }, + { + "epoch": 1.01, + "learning_rate": 1.2136873731871122e-05, + "loss": 3.3685, + "step": 2312704 + }, + { + "epoch": 1.01, + "learning_rate": 1.21284877843606e-05, + "loss": 3.3612, + "step": 2313216 + }, + { + "epoch": 1.01, + "learning_rate": 1.2120101836850082e-05, + "loss": 3.3577, + "step": 2313728 + }, + { + "epoch": 1.01, + "learning_rate": 1.2111732268143293e-05, + "loss": 3.3392, + "step": 2314240 + }, + { + "epoch": 1.01, + "learning_rate": 1.2103346320632773e-05, + "loss": 3.3698, + "step": 2314752 + }, + { + "epoch": 1.01, + "learning_rate": 1.2094960373122253e-05, + "loss": 3.3636, + "step": 2315264 + }, + { + "epoch": 1.01, + "learning_rate": 1.2086574425611733e-05, + "loss": 3.3691, + "step": 2315776 + }, + { + "epoch": 1.01, + "learning_rate": 1.2078188478101213e-05, + "loss": 3.3592, + "step": 2316288 + }, + { + "epoch": 1.01, + "learning_rate": 1.2069818909394425e-05, + "loss": 3.3535, + "step": 2316800 + }, + { + "epoch": 1.01, + "learning_rate": 1.2061432961883903e-05, + "loss": 3.3511, + "step": 2317312 + }, + { + "epoch": 1.01, + "learning_rate": 1.2053047014373383e-05, + "loss": 3.3586, + "step": 2317824 + }, + { + "epoch": 1.01, + "learning_rate": 1.2044661066862863e-05, + "loss": 3.3667, + "step": 2318336 + }, + { + "epoch": 1.01, + "learning_rate": 1.2036275119352343e-05, + "loss": 3.3483, + "step": 2318848 + }, + { + "epoch": 1.01, + "learning_rate": 1.2027889171841823e-05, + "loss": 3.3735, + "step": 2319360 + }, + { + "epoch": 1.01, + "learning_rate": 1.2019503224331303e-05, + "loss": 3.3614, + "step": 2319872 + }, + { + "epoch": 1.01, + "learning_rate": 1.2011133655624516e-05, + "loss": 3.3506, + "step": 2320384 + }, + { + "epoch": 1.01, + "learning_rate": 1.2002747708113994e-05, + "loss": 3.3665, + "step": 2320896 + }, + { + "epoch": 1.01, + "learning_rate": 1.1994361760603474e-05, + "loss": 3.3559, + "step": 2321408 + }, + { + "epoch": 1.01, + "learning_rate": 1.1985975813092955e-05, + "loss": 3.3584, + "step": 2321920 + }, + { + "epoch": 1.01, + "learning_rate": 1.1977589865582434e-05, + "loss": 3.3521, + "step": 2322432 + }, + { + "epoch": 1.01, + "learning_rate": 1.1969220296875644e-05, + "loss": 3.369, + "step": 2322944 + }, + { + "epoch": 1.01, + "learning_rate": 1.1960834349365126e-05, + "loss": 3.356, + "step": 2323456 + }, + { + "epoch": 1.01, + "learning_rate": 1.1952448401854606e-05, + "loss": 3.3548, + "step": 2323968 + }, + { + "epoch": 1.01, + "learning_rate": 1.1944062454344084e-05, + "loss": 3.3526, + "step": 2324480 + }, + { + "epoch": 1.01, + "learning_rate": 1.1935692885637297e-05, + "loss": 3.3534, + "step": 2324992 + }, + { + "epoch": 1.01, + "learning_rate": 1.1927306938126777e-05, + "loss": 3.3605, + "step": 2325504 + }, + { + "epoch": 1.01, + "learning_rate": 1.1918920990616255e-05, + "loss": 3.3723, + "step": 2326016 + }, + { + "epoch": 1.01, + "learning_rate": 1.1910535043105737e-05, + "loss": 3.3621, + "step": 2326528 + }, + { + "epoch": 1.01, + "learning_rate": 1.1902149095595217e-05, + "loss": 3.3616, + "step": 2327040 + }, + { + "epoch": 1.01, + "learning_rate": 1.1893763148084695e-05, + "loss": 3.377, + "step": 2327552 + }, + { + "epoch": 1.01, + "learning_rate": 1.1885377200574175e-05, + "loss": 3.3597, + "step": 2328064 + }, + { + "epoch": 1.01, + "learning_rate": 1.1876991253063657e-05, + "loss": 3.3686, + "step": 2328576 + }, + { + "epoch": 1.01, + "learning_rate": 1.1868621684356867e-05, + "loss": 3.3632, + "step": 2329088 + }, + { + "epoch": 1.01, + "learning_rate": 1.1860235736846347e-05, + "loss": 3.3655, + "step": 2329600 + }, + { + "epoch": 1.01, + "learning_rate": 1.1851849789335827e-05, + "loss": 3.3592, + "step": 2330112 + }, + { + "epoch": 1.01, + "learning_rate": 1.1843463841825307e-05, + "loss": 3.3629, + "step": 2330624 + }, + { + "epoch": 1.01, + "learning_rate": 1.1835094273118518e-05, + "loss": 3.3683, + "step": 2331136 + }, + { + "epoch": 1.01, + "learning_rate": 1.1826708325607998e-05, + "loss": 3.3739, + "step": 2331648 + }, + { + "epoch": 1.01, + "learning_rate": 1.1818322378097478e-05, + "loss": 3.3608, + "step": 2332160 + }, + { + "epoch": 1.01, + "learning_rate": 1.1809936430586958e-05, + "loss": 3.3458, + "step": 2332672 + }, + { + "epoch": 1.01, + "learning_rate": 1.1801550483076438e-05, + "loss": 3.3579, + "step": 2333184 + }, + { + "epoch": 1.01, + "learning_rate": 1.1793180914369649e-05, + "loss": 3.3668, + "step": 2333696 + }, + { + "epoch": 1.01, + "learning_rate": 1.1784794966859129e-05, + "loss": 3.3648, + "step": 2334208 + }, + { + "epoch": 1.01, + "learning_rate": 1.177640901934861e-05, + "loss": 3.3641, + "step": 2334720 + }, + { + "epoch": 1.01, + "learning_rate": 1.1768023071838088e-05, + "loss": 3.3594, + "step": 2335232 + }, + { + "epoch": 1.02, + "learning_rate": 1.1759637124327568e-05, + "loss": 3.3526, + "step": 2335744 + }, + { + "epoch": 1.02, + "learning_rate": 1.1751251176817048e-05, + "loss": 3.357, + "step": 2336256 + }, + { + "epoch": 1.02, + "learning_rate": 1.174288160811026e-05, + "loss": 3.356, + "step": 2336768 + }, + { + "epoch": 1.02, + "learning_rate": 1.1734495660599739e-05, + "loss": 3.3679, + "step": 2337280 + }, + { + "epoch": 1.02, + "learning_rate": 1.172610971308922e-05, + "loss": 3.3683, + "step": 2337792 + }, + { + "epoch": 1.02, + "learning_rate": 1.17177237655787e-05, + "loss": 3.3799, + "step": 2338304 + }, + { + "epoch": 1.02, + "learning_rate": 1.170935419687191e-05, + "loss": 3.3487, + "step": 2338816 + }, + { + "epoch": 1.02, + "learning_rate": 1.1700968249361391e-05, + "loss": 3.3627, + "step": 2339328 + }, + { + "epoch": 1.02, + "learning_rate": 1.1692582301850871e-05, + "loss": 3.3645, + "step": 2339840 + }, + { + "epoch": 1.02, + "learning_rate": 1.168419635434035e-05, + "loss": 3.3647, + "step": 2340352 + }, + { + "epoch": 1.02, + "learning_rate": 1.1675826785633562e-05, + "loss": 3.3662, + "step": 2340864 + }, + { + "epoch": 1.02, + "learning_rate": 1.1667440838123042e-05, + "loss": 3.3637, + "step": 2341376 + }, + { + "epoch": 1.02, + "learning_rate": 1.1659054890612522e-05, + "loss": 3.3634, + "step": 2341888 + }, + { + "epoch": 1.02, + "learning_rate": 1.1650668943102002e-05, + "loss": 3.3549, + "step": 2342400 + }, + { + "epoch": 1.02, + "learning_rate": 1.1642282995591482e-05, + "loss": 3.3706, + "step": 2342912 + }, + { + "epoch": 1.02, + "learning_rate": 1.1633897048080962e-05, + "loss": 3.3459, + "step": 2343424 + }, + { + "epoch": 1.02, + "learning_rate": 1.162551110057044e-05, + "loss": 3.355, + "step": 2343936 + }, + { + "epoch": 1.02, + "learning_rate": 1.1617141531863653e-05, + "loss": 3.3632, + "step": 2344448 + }, + { + "epoch": 1.02, + "learning_rate": 1.1608771963156863e-05, + "loss": 3.3673, + "step": 2344960 + }, + { + "epoch": 1.02, + "learning_rate": 1.1600386015646345e-05, + "loss": 3.3531, + "step": 2345472 + }, + { + "epoch": 1.02, + "learning_rate": 1.1592000068135823e-05, + "loss": 3.3568, + "step": 2345984 + }, + { + "epoch": 1.02, + "learning_rate": 1.1583614120625303e-05, + "loss": 3.3494, + "step": 2346496 + }, + { + "epoch": 1.02, + "learning_rate": 1.1575228173114783e-05, + "loss": 3.362, + "step": 2347008 + }, + { + "epoch": 1.02, + "learning_rate": 1.1566858604407996e-05, + "loss": 3.3579, + "step": 2347520 + }, + { + "epoch": 1.02, + "learning_rate": 1.1558472656897474e-05, + "loss": 3.3663, + "step": 2348032 + }, + { + "epoch": 1.02, + "learning_rate": 1.1550086709386956e-05, + "loss": 3.3719, + "step": 2348544 + }, + { + "epoch": 1.02, + "learning_rate": 1.1541700761876436e-05, + "loss": 3.3732, + "step": 2349056 + }, + { + "epoch": 1.02, + "learning_rate": 1.1533314814365914e-05, + "loss": 3.3537, + "step": 2349568 + }, + { + "epoch": 1.02, + "learning_rate": 1.1524928866855394e-05, + "loss": 3.3616, + "step": 2350080 + }, + { + "epoch": 1.02, + "learning_rate": 1.1516559298148606e-05, + "loss": 3.366, + "step": 2350592 + }, + { + "epoch": 1.02, + "learning_rate": 1.1508173350638086e-05, + "loss": 3.3598, + "step": 2351104 + }, + { + "epoch": 1.02, + "learning_rate": 1.1499787403127565e-05, + "loss": 3.3591, + "step": 2351616 + }, + { + "epoch": 1.02, + "learning_rate": 1.1491401455617046e-05, + "loss": 3.3569, + "step": 2352128 + }, + { + "epoch": 1.02, + "learning_rate": 1.1483015508106526e-05, + "loss": 3.3596, + "step": 2352640 + }, + { + "epoch": 1.02, + "learning_rate": 1.1474645939399737e-05, + "loss": 3.3592, + "step": 2353152 + }, + { + "epoch": 1.02, + "learning_rate": 1.1466259991889217e-05, + "loss": 3.3519, + "step": 2353664 + }, + { + "epoch": 1.02, + "learning_rate": 1.1457874044378697e-05, + "loss": 3.3628, + "step": 2354176 + }, + { + "epoch": 1.02, + "learning_rate": 1.1449488096868177e-05, + "loss": 3.36, + "step": 2354688 + }, + { + "epoch": 1.02, + "learning_rate": 1.1441102149357657e-05, + "loss": 3.3521, + "step": 2355200 + }, + { + "epoch": 1.02, + "learning_rate": 1.1432732580650868e-05, + "loss": 3.3653, + "step": 2355712 + }, + { + "epoch": 1.02, + "learning_rate": 1.1424346633140348e-05, + "loss": 3.366, + "step": 2356224 + }, + { + "epoch": 1.02, + "learning_rate": 1.141596068562983e-05, + "loss": 3.3736, + "step": 2356736 + }, + { + "epoch": 1.02, + "learning_rate": 1.1407574738119307e-05, + "loss": 3.3582, + "step": 2357248 + }, + { + "epoch": 1.02, + "learning_rate": 1.1399188790608787e-05, + "loss": 3.3615, + "step": 2357760 + }, + { + "epoch": 1.02, + "learning_rate": 1.1390802843098267e-05, + "loss": 3.3666, + "step": 2358272 + }, + { + "epoch": 1.02, + "learning_rate": 1.1382416895587747e-05, + "loss": 3.3558, + "step": 2358784 + }, + { + "epoch": 1.02, + "learning_rate": 1.1374047326880958e-05, + "loss": 3.3655, + "step": 2359296 + }, + { + "epoch": 1.02, + "learning_rate": 1.1365661379370438e-05, + "loss": 3.3594, + "step": 2359808 + }, + { + "epoch": 1.02, + "learning_rate": 1.135727543185992e-05, + "loss": 3.3668, + "step": 2360320 + }, + { + "epoch": 1.02, + "learning_rate": 1.1348889484349398e-05, + "loss": 3.3648, + "step": 2360832 + }, + { + "epoch": 1.02, + "learning_rate": 1.1340503536838878e-05, + "loss": 3.3602, + "step": 2361344 + }, + { + "epoch": 1.02, + "learning_rate": 1.133211758932836e-05, + "loss": 3.3605, + "step": 2361856 + }, + { + "epoch": 1.02, + "learning_rate": 1.1323748020621569e-05, + "loss": 3.3649, + "step": 2362368 + }, + { + "epoch": 1.02, + "learning_rate": 1.1315362073111049e-05, + "loss": 3.3551, + "step": 2362880 + }, + { + "epoch": 1.02, + "learning_rate": 1.130697612560053e-05, + "loss": 3.3576, + "step": 2363392 + }, + { + "epoch": 1.02, + "learning_rate": 1.1298590178090009e-05, + "loss": 3.3672, + "step": 2363904 + }, + { + "epoch": 1.02, + "learning_rate": 1.1290204230579489e-05, + "loss": 3.3556, + "step": 2364416 + }, + { + "epoch": 1.02, + "learning_rate": 1.1281818283068968e-05, + "loss": 3.3719, + "step": 2364928 + }, + { + "epoch": 1.02, + "learning_rate": 1.1273448714362181e-05, + "loss": 3.3495, + "step": 2365440 + }, + { + "epoch": 1.03, + "eval_loss": 3.863355875015259, + "eval_runtime": 307.2303, + "eval_samples_per_second": 1242.036, + "eval_steps_per_second": 38.815, + "step": 2365920 + }, + { + "epoch": 0.0, + "learning_rate": 1.126506276685166e-05, + "loss": 3.3308, + "step": 2365952 + }, + { + "epoch": 0.0, + "learning_rate": 1.1256676819341141e-05, + "loss": 3.3552, + "step": 2366464 + }, + { + "epoch": 0.0, + "learning_rate": 1.1248307250634352e-05, + "loss": 3.3558, + "step": 2366976 + }, + { + "epoch": 0.0, + "learning_rate": 1.1239921303123832e-05, + "loss": 3.3673, + "step": 2367488 + }, + { + "epoch": 0.0, + "learning_rate": 1.1231535355613312e-05, + "loss": 3.3668, + "step": 2368000 + }, + { + "epoch": 0.0, + "learning_rate": 1.1223149408102792e-05, + "loss": 3.3668, + "step": 2368512 + }, + { + "epoch": 0.0, + "learning_rate": 1.1214779839396002e-05, + "loss": 3.3566, + "step": 2369024 + }, + { + "epoch": 0.0, + "learning_rate": 1.1206393891885482e-05, + "loss": 3.3546, + "step": 2369536 + }, + { + "epoch": 0.0, + "learning_rate": 1.1198007944374962e-05, + "loss": 3.3541, + "step": 2370048 + }, + { + "epoch": 0.0, + "learning_rate": 1.1189621996864442e-05, + "loss": 3.3639, + "step": 2370560 + }, + { + "epoch": 0.0, + "learning_rate": 1.1181236049353922e-05, + "loss": 3.3558, + "step": 2371072 + }, + { + "epoch": 0.0, + "learning_rate": 1.1172850101843402e-05, + "loss": 3.3646, + "step": 2371584 + }, + { + "epoch": 0.0, + "learning_rate": 1.1164480533136613e-05, + "loss": 3.3637, + "step": 2372096 + }, + { + "epoch": 0.0, + "learning_rate": 1.1156094585626095e-05, + "loss": 3.349, + "step": 2372608 + }, + { + "epoch": 0.0, + "learning_rate": 1.1147708638115573e-05, + "loss": 3.3523, + "step": 2373120 + }, + { + "epoch": 0.0, + "learning_rate": 1.1139322690605053e-05, + "loss": 3.3471, + "step": 2373632 + }, + { + "epoch": 0.0, + "learning_rate": 1.1130936743094533e-05, + "loss": 3.36, + "step": 2374144 + }, + { + "epoch": 0.0, + "learning_rate": 1.1122550795584014e-05, + "loss": 3.3509, + "step": 2374656 + }, + { + "epoch": 0.0, + "learning_rate": 1.1114164848073493e-05, + "loss": 3.354, + "step": 2375168 + }, + { + "epoch": 0.0, + "learning_rate": 1.1105778900562973e-05, + "loss": 3.3556, + "step": 2375680 + }, + { + "epoch": 0.0, + "learning_rate": 1.1097409331856185e-05, + "loss": 3.3652, + "step": 2376192 + }, + { + "epoch": 0.0, + "learning_rate": 1.1089023384345663e-05, + "loss": 3.3649, + "step": 2376704 + }, + { + "epoch": 0.0, + "learning_rate": 1.1080653815638876e-05, + "loss": 3.3567, + "step": 2377216 + }, + { + "epoch": 0.0, + "learning_rate": 1.1072267868128356e-05, + "loss": 3.3576, + "step": 2377728 + }, + { + "epoch": 0.0, + "learning_rate": 1.1063881920617836e-05, + "loss": 3.364, + "step": 2378240 + }, + { + "epoch": 0.0, + "learning_rate": 1.1055495973107314e-05, + "loss": 3.3578, + "step": 2378752 + }, + { + "epoch": 0.0, + "learning_rate": 1.1047126404400526e-05, + "loss": 3.3496, + "step": 2379264 + }, + { + "epoch": 0.0, + "learning_rate": 1.1038740456890006e-05, + "loss": 3.3609, + "step": 2379776 + }, + { + "epoch": 0.0, + "learning_rate": 1.1030354509379486e-05, + "loss": 3.3452, + "step": 2380288 + }, + { + "epoch": 0.0, + "learning_rate": 1.1021968561868966e-05, + "loss": 3.3445, + "step": 2380800 + }, + { + "epoch": 0.01, + "learning_rate": 1.1013582614358446e-05, + "loss": 3.3505, + "step": 2381312 + }, + { + "epoch": 0.01, + "learning_rate": 1.1005213045651657e-05, + "loss": 3.3526, + "step": 2381824 + }, + { + "epoch": 0.01, + "learning_rate": 1.0996827098141137e-05, + "loss": 3.3637, + "step": 2382336 + }, + { + "epoch": 0.01, + "learning_rate": 1.0988441150630617e-05, + "loss": 3.3627, + "step": 2382848 + }, + { + "epoch": 0.01, + "learning_rate": 1.0980055203120097e-05, + "loss": 3.3547, + "step": 2383360 + }, + { + "epoch": 0.01, + "learning_rate": 1.0971669255609577e-05, + "loss": 3.3598, + "step": 2383872 + }, + { + "epoch": 0.01, + "learning_rate": 1.0963283308099057e-05, + "loss": 3.3663, + "step": 2384384 + }, + { + "epoch": 0.01, + "learning_rate": 1.0954913739392268e-05, + "loss": 3.3483, + "step": 2384896 + }, + { + "epoch": 0.01, + "learning_rate": 1.094652779188175e-05, + "loss": 3.3536, + "step": 2385408 + }, + { + "epoch": 0.01, + "learning_rate": 1.0938141844371228e-05, + "loss": 3.3408, + "step": 2385920 + }, + { + "epoch": 0.01, + "learning_rate": 1.0929755896860707e-05, + "loss": 3.3533, + "step": 2386432 + }, + { + "epoch": 0.01, + "learning_rate": 1.092138632815392e-05, + "loss": 3.3541, + "step": 2386944 + }, + { + "epoch": 0.01, + "learning_rate": 1.09130003806434e-05, + "loss": 3.3602, + "step": 2387456 + }, + { + "epoch": 0.01, + "learning_rate": 1.0904614433132878e-05, + "loss": 3.3541, + "step": 2387968 + }, + { + "epoch": 0.01, + "learning_rate": 1.0896228485622358e-05, + "loss": 3.3512, + "step": 2388480 + }, + { + "epoch": 0.01, + "learning_rate": 1.088784253811184e-05, + "loss": 3.3625, + "step": 2388992 + }, + { + "epoch": 0.01, + "learning_rate": 1.0879456590601318e-05, + "loss": 3.3517, + "step": 2389504 + }, + { + "epoch": 0.01, + "learning_rate": 1.0871070643090798e-05, + "loss": 3.3463, + "step": 2390016 + }, + { + "epoch": 0.01, + "learning_rate": 1.086270107438401e-05, + "loss": 3.3292, + "step": 2390528 + }, + { + "epoch": 0.01, + "learning_rate": 1.085431512687349e-05, + "loss": 3.3616, + "step": 2391040 + }, + { + "epoch": 0.01, + "learning_rate": 1.0845929179362969e-05, + "loss": 3.3542, + "step": 2391552 + }, + { + "epoch": 0.01, + "learning_rate": 1.083754323185245e-05, + "loss": 3.3567, + "step": 2392064 + }, + { + "epoch": 0.01, + "learning_rate": 1.082915728434193e-05, + "loss": 3.3516, + "step": 2392576 + }, + { + "epoch": 0.01, + "learning_rate": 1.0820787715635141e-05, + "loss": 3.3439, + "step": 2393088 + }, + { + "epoch": 0.01, + "learning_rate": 1.0812401768124621e-05, + "loss": 3.3401, + "step": 2393600 + }, + { + "epoch": 0.01, + "learning_rate": 1.0804015820614101e-05, + "loss": 3.3443, + "step": 2394112 + }, + { + "epoch": 0.01, + "learning_rate": 1.0795629873103581e-05, + "loss": 3.3585, + "step": 2394624 + }, + { + "epoch": 0.01, + "learning_rate": 1.0787243925593061e-05, + "loss": 3.3422, + "step": 2395136 + }, + { + "epoch": 0.01, + "learning_rate": 1.0778874356886272e-05, + "loss": 3.3605, + "step": 2395648 + }, + { + "epoch": 0.01, + "learning_rate": 1.0770488409375752e-05, + "loss": 3.3508, + "step": 2396160 + }, + { + "epoch": 0.01, + "learning_rate": 1.0762102461865232e-05, + "loss": 3.3432, + "step": 2396672 + }, + { + "epoch": 0.01, + "learning_rate": 1.0753716514354712e-05, + "loss": 3.354, + "step": 2397184 + }, + { + "epoch": 0.01, + "learning_rate": 1.0745346945647922e-05, + "loss": 3.3481, + "step": 2397696 + }, + { + "epoch": 0.01, + "learning_rate": 1.0736960998137404e-05, + "loss": 3.349, + "step": 2398208 + }, + { + "epoch": 0.01, + "learning_rate": 1.0728575050626882e-05, + "loss": 3.3438, + "step": 2398720 + }, + { + "epoch": 0.01, + "learning_rate": 1.0720189103116362e-05, + "loss": 3.3581, + "step": 2399232 + }, + { + "epoch": 0.01, + "learning_rate": 1.0711803155605842e-05, + "loss": 3.3462, + "step": 2399744 + }, + { + "epoch": 0.01, + "learning_rate": 1.0703417208095324e-05, + "loss": 3.3485, + "step": 2400256 + }, + { + "epoch": 0.01, + "learning_rate": 1.0695031260584802e-05, + "loss": 3.3393, + "step": 2400768 + }, + { + "epoch": 0.01, + "learning_rate": 1.0686645313074282e-05, + "loss": 3.3467, + "step": 2401280 + }, + { + "epoch": 0.01, + "learning_rate": 1.0678275744367495e-05, + "loss": 3.3475, + "step": 2401792 + }, + { + "epoch": 0.01, + "learning_rate": 1.0669889796856973e-05, + "loss": 3.3597, + "step": 2402304 + }, + { + "epoch": 0.01, + "learning_rate": 1.0661503849346453e-05, + "loss": 3.3526, + "step": 2402816 + }, + { + "epoch": 0.01, + "learning_rate": 1.0653117901835934e-05, + "loss": 3.3567, + "step": 2403328 + }, + { + "epoch": 0.01, + "learning_rate": 1.0644731954325413e-05, + "loss": 3.3612, + "step": 2403840 + }, + { + "epoch": 0.01, + "learning_rate": 1.0636346006814893e-05, + "loss": 3.357, + "step": 2404352 + }, + { + "epoch": 0.01, + "learning_rate": 1.0627960059304373e-05, + "loss": 3.3544, + "step": 2404864 + }, + { + "epoch": 0.01, + "learning_rate": 1.0619590490597585e-05, + "loss": 3.3583, + "step": 2405376 + }, + { + "epoch": 0.01, + "learning_rate": 1.0611204543087063e-05, + "loss": 3.3582, + "step": 2405888 + }, + { + "epoch": 0.01, + "learning_rate": 1.0602818595576543e-05, + "loss": 3.3529, + "step": 2406400 + }, + { + "epoch": 0.01, + "learning_rate": 1.0594432648066025e-05, + "loss": 3.3529, + "step": 2406912 + }, + { + "epoch": 0.01, + "learning_rate": 1.0586063079359236e-05, + "loss": 3.3641, + "step": 2407424 + }, + { + "epoch": 0.01, + "learning_rate": 1.0577677131848716e-05, + "loss": 3.3609, + "step": 2407936 + }, + { + "epoch": 0.01, + "learning_rate": 1.0569291184338196e-05, + "loss": 3.3509, + "step": 2408448 + }, + { + "epoch": 0.01, + "learning_rate": 1.0560905236827676e-05, + "loss": 3.3349, + "step": 2408960 + }, + { + "epoch": 0.01, + "learning_rate": 1.0552535668120886e-05, + "loss": 3.3454, + "step": 2409472 + }, + { + "epoch": 0.01, + "learning_rate": 1.0544149720610366e-05, + "loss": 3.3586, + "step": 2409984 + }, + { + "epoch": 0.01, + "learning_rate": 1.0535763773099846e-05, + "loss": 3.3545, + "step": 2410496 + }, + { + "epoch": 0.01, + "learning_rate": 1.0527377825589326e-05, + "loss": 3.3565, + "step": 2411008 + }, + { + "epoch": 0.01, + "learning_rate": 1.0518991878078806e-05, + "loss": 3.3529, + "step": 2411520 + }, + { + "epoch": 0.02, + "learning_rate": 1.0510622309372017e-05, + "loss": 3.3438, + "step": 2412032 + }, + { + "epoch": 0.02, + "learning_rate": 1.0502236361861497e-05, + "loss": 3.3429, + "step": 2412544 + }, + { + "epoch": 0.02, + "learning_rate": 1.0493850414350977e-05, + "loss": 3.3468, + "step": 2413056 + }, + { + "epoch": 0.02, + "learning_rate": 1.0485464466840457e-05, + "loss": 3.359, + "step": 2413568 + }, + { + "epoch": 0.02, + "learning_rate": 1.047709489813367e-05, + "loss": 3.3559, + "step": 2414080 + }, + { + "epoch": 0.02, + "learning_rate": 1.046870895062315e-05, + "loss": 3.3691, + "step": 2414592 + }, + { + "epoch": 0.02, + "learning_rate": 1.0460323003112628e-05, + "loss": 3.345, + "step": 2415104 + }, + { + "epoch": 0.02, + "learning_rate": 1.0451937055602108e-05, + "loss": 3.3531, + "step": 2415616 + }, + { + "epoch": 0.02, + "learning_rate": 1.044355110809159e-05, + "loss": 3.3533, + "step": 2416128 + }, + { + "epoch": 0.02, + "learning_rate": 1.0435165160581067e-05, + "loss": 3.3552, + "step": 2416640 + }, + { + "epoch": 0.02, + "learning_rate": 1.0426795591874278e-05, + "loss": 3.356, + "step": 2417152 + }, + { + "epoch": 0.02, + "learning_rate": 1.041840964436376e-05, + "loss": 3.3559, + "step": 2417664 + }, + { + "epoch": 0.02, + "learning_rate": 1.041002369685324e-05, + "loss": 3.3535, + "step": 2418176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0401637749342718e-05, + "loss": 3.3435, + "step": 2418688 + }, + { + "epoch": 0.02, + "learning_rate": 1.03932518018322e-05, + "loss": 3.3634, + "step": 2419200 + }, + { + "epoch": 0.02, + "learning_rate": 1.038486585432168e-05, + "loss": 3.3389, + "step": 2419712 + }, + { + "epoch": 0.02, + "learning_rate": 1.0376479906811158e-05, + "loss": 3.3449, + "step": 2420224 + }, + { + "epoch": 0.02, + "learning_rate": 1.036811033810437e-05, + "loss": 3.3533, + "step": 2420736 + }, + { + "epoch": 0.02, + "learning_rate": 1.0359740769397581e-05, + "loss": 3.3536, + "step": 2421248 + }, + { + "epoch": 0.02, + "learning_rate": 1.0351354821887061e-05, + "loss": 3.3422, + "step": 2421760 + }, + { + "epoch": 0.02, + "learning_rate": 1.0342968874376541e-05, + "loss": 3.3535, + "step": 2422272 + }, + { + "epoch": 0.02, + "learning_rate": 1.0334582926866021e-05, + "loss": 3.3372, + "step": 2422784 + }, + { + "epoch": 0.02, + "learning_rate": 1.0326213358159232e-05, + "loss": 3.3549, + "step": 2423296 + }, + { + "epoch": 0.02, + "learning_rate": 1.0317827410648714e-05, + "loss": 3.3512, + "step": 2423808 + }, + { + "epoch": 0.02, + "learning_rate": 1.0309441463138192e-05, + "loss": 3.3555, + "step": 2424320 + }, + { + "epoch": 0.02, + "learning_rate": 1.0301055515627672e-05, + "loss": 3.3603, + "step": 2424832 + }, + { + "epoch": 0.02, + "learning_rate": 1.0292685946920884e-05, + "loss": 3.3618, + "step": 2425344 + }, + { + "epoch": 0.02, + "learning_rate": 1.0284299999410364e-05, + "loss": 3.3489, + "step": 2425856 + }, + { + "epoch": 0.02, + "learning_rate": 1.0275914051899842e-05, + "loss": 3.3544, + "step": 2426368 + }, + { + "epoch": 0.02, + "learning_rate": 1.0267528104389324e-05, + "loss": 3.3525, + "step": 2426880 + }, + { + "epoch": 0.02, + "learning_rate": 1.0259142156878804e-05, + "loss": 3.346, + "step": 2427392 + }, + { + "epoch": 0.02, + "learning_rate": 1.0250772588172013e-05, + "loss": 3.3506, + "step": 2427904 + }, + { + "epoch": 0.02, + "learning_rate": 1.0242386640661495e-05, + "loss": 3.3455, + "step": 2428416 + }, + { + "epoch": 0.02, + "learning_rate": 1.0234000693150975e-05, + "loss": 3.3517, + "step": 2428928 + }, + { + "epoch": 0.02, + "learning_rate": 1.0225614745640455e-05, + "loss": 3.3463, + "step": 2429440 + }, + { + "epoch": 0.02, + "learning_rate": 1.0217245176933666e-05, + "loss": 3.3453, + "step": 2429952 + }, + { + "epoch": 0.02, + "learning_rate": 1.0208859229423145e-05, + "loss": 3.3513, + "step": 2430464 + }, + { + "epoch": 0.02, + "learning_rate": 1.0200473281912625e-05, + "loss": 3.349, + "step": 2430976 + }, + { + "epoch": 0.02, + "learning_rate": 1.0192087334402105e-05, + "loss": 3.3444, + "step": 2431488 + }, + { + "epoch": 0.02, + "learning_rate": 1.0183717765695316e-05, + "loss": 3.3507, + "step": 2432000 + }, + { + "epoch": 0.02, + "learning_rate": 1.0175331818184796e-05, + "loss": 3.3573, + "step": 2432512 + }, + { + "epoch": 0.02, + "learning_rate": 1.0166945870674278e-05, + "loss": 3.3665, + "step": 2433024 + }, + { + "epoch": 0.02, + "learning_rate": 1.0158559923163756e-05, + "loss": 3.3446, + "step": 2433536 + }, + { + "epoch": 0.02, + "learning_rate": 1.0150173975653236e-05, + "loss": 3.3489, + "step": 2434048 + }, + { + "epoch": 0.02, + "learning_rate": 1.0141788028142716e-05, + "loss": 3.3556, + "step": 2434560 + }, + { + "epoch": 0.02, + "learning_rate": 1.0133402080632196e-05, + "loss": 3.3497, + "step": 2435072 + }, + { + "epoch": 0.02, + "learning_rate": 1.0125032511925407e-05, + "loss": 3.3532, + "step": 2435584 + }, + { + "epoch": 0.02, + "learning_rate": 1.0116646564414887e-05, + "loss": 3.3503, + "step": 2436096 + }, + { + "epoch": 0.02, + "learning_rate": 1.0108260616904368e-05, + "loss": 3.3569, + "step": 2436608 + }, + { + "epoch": 0.02, + "learning_rate": 1.0099874669393847e-05, + "loss": 3.3506, + "step": 2437120 + }, + { + "epoch": 0.02, + "learning_rate": 1.0091488721883327e-05, + "loss": 3.3531, + "step": 2437632 + }, + { + "epoch": 0.02, + "learning_rate": 1.0083119153176539e-05, + "loss": 3.3522, + "step": 2438144 + }, + { + "epoch": 0.02, + "learning_rate": 1.0074733205666017e-05, + "loss": 3.3506, + "step": 2438656 + }, + { + "epoch": 0.02, + "learning_rate": 1.0066347258155497e-05, + "loss": 3.3486, + "step": 2439168 + }, + { + "epoch": 0.02, + "learning_rate": 1.0057961310644979e-05, + "loss": 3.347, + "step": 2439680 + }, + { + "epoch": 0.02, + "learning_rate": 1.004959174193819e-05, + "loss": 3.3566, + "step": 2440192 + }, + { + "epoch": 0.02, + "learning_rate": 1.004120579442767e-05, + "loss": 3.3485, + "step": 2440704 + }, + { + "epoch": 0.02, + "learning_rate": 1.003281984691715e-05, + "loss": 3.3598, + "step": 2441216 + }, + { + "epoch": 0.02, + "learning_rate": 1.002443389940663e-05, + "loss": 3.3395, + "step": 2441728 + }, + { + "epoch": 0.03, + "learning_rate": 1.0016047951896108e-05, + "loss": 3.3497, + "step": 2442240 + }, + { + "epoch": 0.03, + "eval_loss": 3.8635222911834717, + "eval_runtime": 345.4253, + "eval_samples_per_second": 1104.699, + "eval_steps_per_second": 34.523, + "step": 2442240 + }, + { + "epoch": 1.0, + "learning_rate": 1.000767838318932e-05, + "loss": 3.344, + "step": 2442752 + }, + { + "epoch": 1.0, + "learning_rate": 9.9992924356788e-06, + "loss": 3.3466, + "step": 2443264 + }, + { + "epoch": 1.0, + "learning_rate": 9.99090648816828e-06, + "loss": 3.358, + "step": 2443776 + }, + { + "epoch": 1.0, + "learning_rate": 9.98252054065776e-06, + "loss": 3.356, + "step": 2444288 + }, + { + "epoch": 1.0, + "learning_rate": 9.974150971950971e-06, + "loss": 3.3604, + "step": 2444800 + }, + { + "epoch": 1.0, + "learning_rate": 9.965765024440451e-06, + "loss": 3.3476, + "step": 2445312 + }, + { + "epoch": 1.0, + "learning_rate": 9.957379076929933e-06, + "loss": 3.346, + "step": 2445824 + }, + { + "epoch": 1.0, + "learning_rate": 9.94899312941941e-06, + "loss": 3.3374, + "step": 2446336 + }, + { + "epoch": 1.0, + "learning_rate": 9.94060718190889e-06, + "loss": 3.357, + "step": 2446848 + }, + { + "epoch": 1.0, + "learning_rate": 9.93222123439837e-06, + "loss": 3.3448, + "step": 2447360 + }, + { + "epoch": 1.0, + "learning_rate": 9.92383528688785e-06, + "loss": 3.3591, + "step": 2447872 + }, + { + "epoch": 1.0, + "learning_rate": 9.915465718181061e-06, + "loss": 3.3525, + "step": 2448384 + }, + { + "epoch": 1.0, + "learning_rate": 9.907079770670543e-06, + "loss": 3.3428, + "step": 2448896 + }, + { + "epoch": 1.0, + "learning_rate": 9.898693823160023e-06, + "loss": 3.3388, + "step": 2449408 + }, + { + "epoch": 1.0, + "learning_rate": 9.890307875649501e-06, + "loss": 3.3392, + "step": 2449920 + }, + { + "epoch": 1.0, + "learning_rate": 9.881921928138981e-06, + "loss": 3.3464, + "step": 2450432 + }, + { + "epoch": 1.0, + "learning_rate": 9.873535980628463e-06, + "loss": 3.3446, + "step": 2450944 + }, + { + "epoch": 1.0, + "learning_rate": 9.865150033117941e-06, + "loss": 3.3439, + "step": 2451456 + }, + { + "epoch": 1.0, + "learning_rate": 9.856764085607421e-06, + "loss": 3.3467, + "step": 2451968 + }, + { + "epoch": 1.0, + "learning_rate": 9.848394516900634e-06, + "loss": 3.359, + "step": 2452480 + }, + { + "epoch": 1.0, + "learning_rate": 9.840008569390114e-06, + "loss": 3.3514, + "step": 2452992 + }, + { + "epoch": 1.0, + "learning_rate": 9.831639000683324e-06, + "loss": 3.3518, + "step": 2453504 + }, + { + "epoch": 1.0, + "learning_rate": 9.823253053172804e-06, + "loss": 3.3462, + "step": 2454016 + }, + { + "epoch": 1.0, + "learning_rate": 9.814867105662284e-06, + "loss": 3.3564, + "step": 2454528 + }, + { + "epoch": 1.0, + "learning_rate": 9.806481158151763e-06, + "loss": 3.3467, + "step": 2455040 + }, + { + "epoch": 1.0, + "learning_rate": 9.798111589444975e-06, + "loss": 3.344, + "step": 2455552 + }, + { + "epoch": 1.0, + "learning_rate": 9.789725641934455e-06, + "loss": 3.3487, + "step": 2456064 + }, + { + "epoch": 1.0, + "learning_rate": 9.781339694423935e-06, + "loss": 3.3352, + "step": 2456576 + }, + { + "epoch": 1.0, + "learning_rate": 9.772953746913415e-06, + "loss": 3.3384, + "step": 2457088 + }, + { + "epoch": 1.01, + "learning_rate": 9.764567799402895e-06, + "loss": 3.3398, + "step": 2457600 + }, + { + "epoch": 1.01, + "learning_rate": 9.756181851892375e-06, + "loss": 3.3482, + "step": 2458112 + }, + { + "epoch": 1.01, + "learning_rate": 9.747812283185587e-06, + "loss": 3.3484, + "step": 2458624 + }, + { + "epoch": 1.01, + "learning_rate": 9.739426335675066e-06, + "loss": 3.3552, + "step": 2459136 + }, + { + "epoch": 1.01, + "learning_rate": 9.731040388164546e-06, + "loss": 3.3493, + "step": 2459648 + }, + { + "epoch": 1.01, + "learning_rate": 9.722654440654025e-06, + "loss": 3.3503, + "step": 2460160 + }, + { + "epoch": 1.01, + "learning_rate": 9.714268493143505e-06, + "loss": 3.3548, + "step": 2460672 + }, + { + "epoch": 1.01, + "learning_rate": 9.705898924436716e-06, + "loss": 3.3386, + "step": 2461184 + }, + { + "epoch": 1.01, + "learning_rate": 9.697512976926198e-06, + "loss": 3.3448, + "step": 2461696 + }, + { + "epoch": 1.01, + "learning_rate": 9.689127029415678e-06, + "loss": 3.3336, + "step": 2462208 + }, + { + "epoch": 1.01, + "learning_rate": 9.680741081905156e-06, + "loss": 3.3484, + "step": 2462720 + }, + { + "epoch": 1.01, + "learning_rate": 9.672371513198369e-06, + "loss": 3.3403, + "step": 2463232 + }, + { + "epoch": 1.01, + "learning_rate": 9.663985565687849e-06, + "loss": 3.3554, + "step": 2463744 + }, + { + "epoch": 1.01, + "learning_rate": 9.655599618177327e-06, + "loss": 3.3441, + "step": 2464256 + }, + { + "epoch": 1.01, + "learning_rate": 9.647213670666807e-06, + "loss": 3.3437, + "step": 2464768 + }, + { + "epoch": 1.01, + "learning_rate": 9.638827723156288e-06, + "loss": 3.3505, + "step": 2465280 + }, + { + "epoch": 1.01, + "learning_rate": 9.630441775645768e-06, + "loss": 3.3418, + "step": 2465792 + }, + { + "epoch": 1.01, + "learning_rate": 9.622055828135247e-06, + "loss": 3.3392, + "step": 2466304 + }, + { + "epoch": 1.01, + "learning_rate": 9.613686259428459e-06, + "loss": 3.3213, + "step": 2466816 + }, + { + "epoch": 1.01, + "learning_rate": 9.605300311917939e-06, + "loss": 3.347, + "step": 2467328 + }, + { + "epoch": 1.01, + "learning_rate": 9.596914364407417e-06, + "loss": 3.3499, + "step": 2467840 + }, + { + "epoch": 1.01, + "learning_rate": 9.588528416896899e-06, + "loss": 3.3451, + "step": 2468352 + }, + { + "epoch": 1.01, + "learning_rate": 9.580142469386379e-06, + "loss": 3.3396, + "step": 2468864 + }, + { + "epoch": 1.01, + "learning_rate": 9.57177290067959e-06, + "loss": 3.3361, + "step": 2469376 + }, + { + "epoch": 1.01, + "learning_rate": 9.56338695316907e-06, + "loss": 3.3323, + "step": 2469888 + }, + { + "epoch": 1.01, + "learning_rate": 9.55500100565855e-06, + "loss": 3.3294, + "step": 2470400 + }, + { + "epoch": 1.01, + "learning_rate": 9.54661505814803e-06, + "loss": 3.3543, + "step": 2470912 + }, + { + "epoch": 1.01, + "learning_rate": 9.53822911063751e-06, + "loss": 3.3307, + "step": 2471424 + }, + { + "epoch": 1.01, + "learning_rate": 9.52985954193072e-06, + "loss": 3.3485, + "step": 2471936 + }, + { + "epoch": 1.01, + "learning_rate": 9.5214735944202e-06, + "loss": 3.3465, + "step": 2472448 + }, + { + "epoch": 1.01, + "learning_rate": 9.51308764690968e-06, + "loss": 3.3309, + "step": 2472960 + }, + { + "epoch": 1.01, + "learning_rate": 9.50470169939916e-06, + "loss": 3.3468, + "step": 2473472 + }, + { + "epoch": 1.01, + "learning_rate": 9.496332130692371e-06, + "loss": 3.3385, + "step": 2473984 + }, + { + "epoch": 1.01, + "learning_rate": 9.487946183181853e-06, + "loss": 3.3396, + "step": 2474496 + }, + { + "epoch": 1.01, + "learning_rate": 9.479560235671333e-06, + "loss": 3.3337, + "step": 2475008 + }, + { + "epoch": 1.01, + "learning_rate": 9.471174288160811e-06, + "loss": 3.3498, + "step": 2475520 + }, + { + "epoch": 1.01, + "learning_rate": 9.46278834065029e-06, + "loss": 3.337, + "step": 2476032 + }, + { + "epoch": 1.01, + "learning_rate": 9.454402393139772e-06, + "loss": 3.3348, + "step": 2476544 + }, + { + "epoch": 1.01, + "learning_rate": 9.446032824432982e-06, + "loss": 3.3349, + "step": 2477056 + }, + { + "epoch": 1.01, + "learning_rate": 9.437646876922463e-06, + "loss": 3.3364, + "step": 2477568 + }, + { + "epoch": 1.01, + "learning_rate": 9.429260929411943e-06, + "loss": 3.3385, + "step": 2478080 + }, + { + "epoch": 1.01, + "learning_rate": 9.420874981901421e-06, + "loss": 3.3519, + "step": 2478592 + }, + { + "epoch": 1.01, + "learning_rate": 9.412505413194634e-06, + "loss": 3.3397, + "step": 2479104 + }, + { + "epoch": 1.01, + "learning_rate": 9.404119465684114e-06, + "loss": 3.3485, + "step": 2479616 + }, + { + "epoch": 1.01, + "learning_rate": 9.395733518173594e-06, + "loss": 3.3529, + "step": 2480128 + }, + { + "epoch": 1.01, + "learning_rate": 9.387347570663072e-06, + "loss": 3.3466, + "step": 2480640 + }, + { + "epoch": 1.01, + "learning_rate": 9.378961623152554e-06, + "loss": 3.3448, + "step": 2481152 + }, + { + "epoch": 1.01, + "learning_rate": 9.370592054445765e-06, + "loss": 3.3473, + "step": 2481664 + }, + { + "epoch": 1.01, + "learning_rate": 9.362206106935244e-06, + "loss": 3.349, + "step": 2482176 + }, + { + "epoch": 1.01, + "learning_rate": 9.353820159424724e-06, + "loss": 3.3417, + "step": 2482688 + }, + { + "epoch": 1.01, + "learning_rate": 9.345434211914204e-06, + "loss": 3.3412, + "step": 2483200 + }, + { + "epoch": 1.01, + "learning_rate": 9.337064643207417e-06, + "loss": 3.3552, + "step": 2483712 + }, + { + "epoch": 1.01, + "learning_rate": 9.328678695696895e-06, + "loss": 3.3534, + "step": 2484224 + }, + { + "epoch": 1.01, + "learning_rate": 9.320292748186375e-06, + "loss": 3.3399, + "step": 2484736 + }, + { + "epoch": 1.01, + "learning_rate": 9.311906800675855e-06, + "loss": 3.3257, + "step": 2485248 + }, + { + "epoch": 1.01, + "learning_rate": 9.303520853165337e-06, + "loss": 3.3374, + "step": 2485760 + }, + { + "epoch": 1.01, + "learning_rate": 9.295134905654815e-06, + "loss": 3.3523, + "step": 2486272 + }, + { + "epoch": 1.01, + "learning_rate": 9.286748958144295e-06, + "loss": 3.3429, + "step": 2486784 + }, + { + "epoch": 1.01, + "learning_rate": 9.278379389437507e-06, + "loss": 3.349, + "step": 2487296 + }, + { + "epoch": 1.01, + "learning_rate": 9.269993441926986e-06, + "loss": 3.3379, + "step": 2487808 + }, + { + "epoch": 1.02, + "learning_rate": 9.261607494416466e-06, + "loss": 3.3422, + "step": 2488320 + }, + { + "epoch": 1.02, + "learning_rate": 9.253221546905946e-06, + "loss": 3.3346, + "step": 2488832 + }, + { + "epoch": 1.02, + "learning_rate": 9.244835599395427e-06, + "loss": 3.3366, + "step": 2489344 + }, + { + "epoch": 1.02, + "learning_rate": 9.236449651884905e-06, + "loss": 3.3471, + "step": 2489856 + }, + { + "epoch": 1.02, + "learning_rate": 9.228080083178118e-06, + "loss": 3.3454, + "step": 2490368 + }, + { + "epoch": 1.02, + "learning_rate": 9.219694135667598e-06, + "loss": 3.3581, + "step": 2490880 + }, + { + "epoch": 1.02, + "learning_rate": 9.211308188157076e-06, + "loss": 3.3423, + "step": 2491392 + }, + { + "epoch": 1.02, + "learning_rate": 9.202922240646556e-06, + "loss": 3.3385, + "step": 2491904 + }, + { + "epoch": 1.02, + "learning_rate": 9.194536293136038e-06, + "loss": 3.3471, + "step": 2492416 + }, + { + "epoch": 1.02, + "learning_rate": 9.186150345625518e-06, + "loss": 3.3461, + "step": 2492928 + }, + { + "epoch": 1.02, + "learning_rate": 9.177780776918727e-06, + "loss": 3.346, + "step": 2493440 + }, + { + "epoch": 1.02, + "learning_rate": 9.169394829408208e-06, + "loss": 3.3465, + "step": 2493952 + }, + { + "epoch": 1.02, + "learning_rate": 9.161008881897688e-06, + "loss": 3.3427, + "step": 2494464 + }, + { + "epoch": 1.02, + "learning_rate": 9.152622934387167e-06, + "loss": 3.3378, + "step": 2494976 + }, + { + "epoch": 1.02, + "learning_rate": 9.144236986876648e-06, + "loss": 3.3483, + "step": 2495488 + }, + { + "epoch": 1.02, + "learning_rate": 9.135851039366128e-06, + "loss": 3.3318, + "step": 2496000 + }, + { + "epoch": 1.02, + "learning_rate": 9.127481470659339e-06, + "loss": 3.3353, + "step": 2496512 + }, + { + "epoch": 1.02, + "learning_rate": 9.119095523148819e-06, + "loss": 3.3446, + "step": 2497024 + }, + { + "epoch": 1.02, + "learning_rate": 9.110709575638299e-06, + "loss": 3.3399, + "step": 2497536 + }, + { + "epoch": 1.02, + "learning_rate": 9.102323628127779e-06, + "loss": 3.3323, + "step": 2498048 + }, + { + "epoch": 1.02, + "learning_rate": 9.093937680617257e-06, + "loss": 3.3478, + "step": 2498560 + }, + { + "epoch": 1.02, + "learning_rate": 9.08556811191047e-06, + "loss": 3.3303, + "step": 2499072 + }, + { + "epoch": 1.02, + "learning_rate": 9.07718216439995e-06, + "loss": 3.3439, + "step": 2499584 + }, + { + "epoch": 1.02, + "learning_rate": 9.06879621688943e-06, + "loss": 3.339, + "step": 2500096 + }, + { + "epoch": 1.02, + "learning_rate": 9.06041026937891e-06, + "loss": 3.3459, + "step": 2500608 + }, + { + "epoch": 1.02, + "learning_rate": 9.05202432186839e-06, + "loss": 3.354, + "step": 2501120 + }, + { + "epoch": 1.02, + "learning_rate": 9.04363837435787e-06, + "loss": 3.352, + "step": 2501632 + }, + { + "epoch": 1.02, + "learning_rate": 9.03525242684735e-06, + "loss": 3.3381, + "step": 2502144 + }, + { + "epoch": 1.02, + "learning_rate": 9.02686647933683e-06, + "loss": 3.3452, + "step": 2502656 + }, + { + "epoch": 1.02, + "learning_rate": 9.01849691063004e-06, + "loss": 3.347, + "step": 2503168 + }, + { + "epoch": 1.02, + "learning_rate": 9.010110963119522e-06, + "loss": 3.3353, + "step": 2503680 + }, + { + "epoch": 1.02, + "learning_rate": 9.001725015609e-06, + "loss": 3.3414, + "step": 2504192 + }, + { + "epoch": 1.02, + "learning_rate": 8.99333906809848e-06, + "loss": 3.3365, + "step": 2504704 + }, + { + "epoch": 1.02, + "learning_rate": 8.98495312058796e-06, + "loss": 3.3403, + "step": 2505216 + }, + { + "epoch": 1.02, + "learning_rate": 8.976583551881173e-06, + "loss": 3.3416, + "step": 2505728 + }, + { + "epoch": 1.02, + "learning_rate": 8.96819760437065e-06, + "loss": 3.3354, + "step": 2506240 + }, + { + "epoch": 1.02, + "learning_rate": 8.95981165686013e-06, + "loss": 3.3441, + "step": 2506752 + }, + { + "epoch": 1.02, + "learning_rate": 8.951425709349612e-06, + "loss": 3.3408, + "step": 2507264 + }, + { + "epoch": 1.02, + "learning_rate": 8.94303976183909e-06, + "loss": 3.3371, + "step": 2507776 + }, + { + "epoch": 1.02, + "learning_rate": 8.934670193132303e-06, + "loss": 3.3367, + "step": 2508288 + }, + { + "epoch": 1.02, + "learning_rate": 8.926284245621783e-06, + "loss": 3.3529, + "step": 2508800 + }, + { + "epoch": 1.02, + "learning_rate": 8.917898298111263e-06, + "loss": 3.3574, + "step": 2509312 + }, + { + "epoch": 1.02, + "learning_rate": 8.909512350600741e-06, + "loss": 3.3437, + "step": 2509824 + }, + { + "epoch": 1.02, + "learning_rate": 8.901126403090223e-06, + "loss": 3.3322, + "step": 2510336 + }, + { + "epoch": 1.02, + "learning_rate": 8.892740455579703e-06, + "loss": 3.3429, + "step": 2510848 + }, + { + "epoch": 1.02, + "learning_rate": 8.884354508069181e-06, + "loss": 3.3433, + "step": 2511360 + }, + { + "epoch": 1.02, + "learning_rate": 8.875984939362394e-06, + "loss": 3.3459, + "step": 2511872 + }, + { + "epoch": 1.02, + "learning_rate": 8.867598991851874e-06, + "loss": 3.3449, + "step": 2512384 + }, + { + "epoch": 1.02, + "learning_rate": 8.859213044341352e-06, + "loss": 3.3487, + "step": 2512896 + }, + { + "epoch": 1.02, + "learning_rate": 8.850827096830834e-06, + "loss": 3.34, + "step": 2513408 + }, + { + "epoch": 1.02, + "learning_rate": 8.842457528124044e-06, + "loss": 3.3438, + "step": 2513920 + }, + { + "epoch": 1.02, + "learning_rate": 8.834071580613524e-06, + "loss": 3.3396, + "step": 2514432 + }, + { + "epoch": 1.02, + "learning_rate": 8.825685633103004e-06, + "loss": 3.343, + "step": 2514944 + }, + { + "epoch": 1.02, + "learning_rate": 8.817299685592484e-06, + "loss": 3.3371, + "step": 2515456 + }, + { + "epoch": 1.02, + "learning_rate": 8.808930116885695e-06, + "loss": 3.3343, + "step": 2515968 + }, + { + "epoch": 1.02, + "learning_rate": 8.800544169375177e-06, + "loss": 3.3523, + "step": 2516480 + }, + { + "epoch": 1.02, + "learning_rate": 8.792158221864655e-06, + "loss": 3.3378, + "step": 2516992 + }, + { + "epoch": 1.02, + "learning_rate": 8.783772274354135e-06, + "loss": 3.3503, + "step": 2517504 + }, + { + "epoch": 1.02, + "learning_rate": 8.775402705647347e-06, + "loss": 3.3348, + "step": 2518016 + }, + { + "epoch": 1.02, + "learning_rate": 8.767016758136826e-06, + "loss": 3.3351, + "step": 2518528 + }, + { + "epoch": 1.03, + "eval_loss": 3.8644254207611084, + "eval_runtime": 340.9503, + "eval_samples_per_second": 1119.198, + "eval_steps_per_second": 34.976, + "step": 2518560 + }, + { + "epoch": 0.0, + "learning_rate": 8.758647189430038e-06, + "loss": 3.334, + "step": 2519040 + }, + { + "epoch": 0.0, + "learning_rate": 8.750261241919518e-06, + "loss": 3.3421, + "step": 2519552 + }, + { + "epoch": 0.0, + "learning_rate": 8.741875294408998e-06, + "loss": 3.348, + "step": 2520064 + }, + { + "epoch": 0.0, + "learning_rate": 8.733489346898476e-06, + "loss": 3.3419, + "step": 2520576 + }, + { + "epoch": 0.0, + "learning_rate": 8.725119778191689e-06, + "loss": 3.3521, + "step": 2521088 + }, + { + "epoch": 0.0, + "learning_rate": 8.716733830681169e-06, + "loss": 3.3391, + "step": 2521600 + }, + { + "epoch": 0.0, + "learning_rate": 8.708347883170649e-06, + "loss": 3.3338, + "step": 2522112 + }, + { + "epoch": 0.0, + "learning_rate": 8.699961935660129e-06, + "loss": 3.332, + "step": 2522624 + }, + { + "epoch": 0.0, + "learning_rate": 8.691575988149609e-06, + "loss": 3.3451, + "step": 2523136 + }, + { + "epoch": 0.0, + "learning_rate": 8.683190040639088e-06, + "loss": 3.3377, + "step": 2523648 + }, + { + "epoch": 0.0, + "learning_rate": 8.674804093128568e-06, + "loss": 3.3508, + "step": 2524160 + }, + { + "epoch": 0.0, + "learning_rate": 8.66643452442178e-06, + "loss": 3.3418, + "step": 2524672 + }, + { + "epoch": 0.0, + "learning_rate": 8.65804857691126e-06, + "loss": 3.3346, + "step": 2525184 + }, + { + "epoch": 0.0, + "learning_rate": 8.649662629400739e-06, + "loss": 3.3292, + "step": 2525696 + }, + { + "epoch": 0.0, + "learning_rate": 8.641276681890219e-06, + "loss": 3.3329, + "step": 2526208 + }, + { + "epoch": 0.0, + "learning_rate": 8.632890734379699e-06, + "loss": 3.3315, + "step": 2526720 + }, + { + "epoch": 0.0, + "learning_rate": 8.624504786869179e-06, + "loss": 3.3363, + "step": 2527232 + }, + { + "epoch": 0.0, + "learning_rate": 8.616118839358659e-06, + "loss": 3.3341, + "step": 2527744 + }, + { + "epoch": 0.0, + "learning_rate": 8.607732891848139e-06, + "loss": 3.3315, + "step": 2528256 + }, + { + "epoch": 0.0, + "learning_rate": 8.59936332314135e-06, + "loss": 3.3549, + "step": 2528768 + }, + { + "epoch": 0.0, + "learning_rate": 8.590977375630831e-06, + "loss": 3.3407, + "step": 2529280 + }, + { + "epoch": 0.0, + "learning_rate": 8.58260780692404e-06, + "loss": 3.3433, + "step": 2529792 + }, + { + "epoch": 0.0, + "learning_rate": 8.57422185941352e-06, + "loss": 3.3359, + "step": 2530304 + }, + { + "epoch": 0.0, + "learning_rate": 8.565835911903002e-06, + "loss": 3.3472, + "step": 2530816 + }, + { + "epoch": 0.0, + "learning_rate": 8.55744996439248e-06, + "loss": 3.3334, + "step": 2531328 + }, + { + "epoch": 0.0, + "learning_rate": 8.54906401688196e-06, + "loss": 3.3365, + "step": 2531840 + }, + { + "epoch": 0.0, + "learning_rate": 8.540678069371442e-06, + "loss": 3.3364, + "step": 2532352 + }, + { + "epoch": 0.0, + "learning_rate": 8.532308500664653e-06, + "loss": 3.3329, + "step": 2532864 + }, + { + "epoch": 0.0, + "learning_rate": 8.523922553154131e-06, + "loss": 3.326, + "step": 2533376 + }, + { + "epoch": 0.01, + "learning_rate": 8.515536605643613e-06, + "loss": 3.3293, + "step": 2533888 + }, + { + "epoch": 0.01, + "learning_rate": 8.507150658133093e-06, + "loss": 3.3408, + "step": 2534400 + }, + { + "epoch": 0.01, + "learning_rate": 8.498764710622571e-06, + "loss": 3.341, + "step": 2534912 + }, + { + "epoch": 0.01, + "learning_rate": 8.49037876311205e-06, + "loss": 3.3424, + "step": 2535424 + }, + { + "epoch": 0.01, + "learning_rate": 8.482009194405263e-06, + "loss": 3.3439, + "step": 2535936 + }, + { + "epoch": 0.01, + "learning_rate": 8.473623246894743e-06, + "loss": 3.3401, + "step": 2536448 + }, + { + "epoch": 0.01, + "learning_rate": 8.465237299384223e-06, + "loss": 3.3422, + "step": 2536960 + }, + { + "epoch": 0.01, + "learning_rate": 8.456851351873703e-06, + "loss": 3.3328, + "step": 2537472 + }, + { + "epoch": 0.01, + "learning_rate": 8.448481783166914e-06, + "loss": 3.3387, + "step": 2537984 + }, + { + "epoch": 0.01, + "learning_rate": 8.440095835656394e-06, + "loss": 3.3233, + "step": 2538496 + }, + { + "epoch": 0.01, + "learning_rate": 8.431709888145874e-06, + "loss": 3.3399, + "step": 2539008 + }, + { + "epoch": 0.01, + "learning_rate": 8.423323940635354e-06, + "loss": 3.3317, + "step": 2539520 + }, + { + "epoch": 0.01, + "learning_rate": 8.414937993124834e-06, + "loss": 3.3449, + "step": 2540032 + }, + { + "epoch": 0.01, + "learning_rate": 8.406568424418045e-06, + "loss": 3.3334, + "step": 2540544 + }, + { + "epoch": 0.01, + "learning_rate": 8.398182476907525e-06, + "loss": 3.3365, + "step": 2541056 + }, + { + "epoch": 0.01, + "learning_rate": 8.389796529397004e-06, + "loss": 3.339, + "step": 2541568 + }, + { + "epoch": 0.01, + "learning_rate": 8.381410581886486e-06, + "loss": 3.3351, + "step": 2542080 + }, + { + "epoch": 0.01, + "learning_rate": 8.373041013179695e-06, + "loss": 3.3293, + "step": 2542592 + }, + { + "epoch": 0.01, + "learning_rate": 8.364655065669177e-06, + "loss": 3.3178, + "step": 2543104 + }, + { + "epoch": 0.01, + "learning_rate": 8.356269118158657e-06, + "loss": 3.3294, + "step": 2543616 + }, + { + "epoch": 0.01, + "learning_rate": 8.347883170648135e-06, + "loss": 3.3409, + "step": 2544128 + }, + { + "epoch": 0.01, + "learning_rate": 8.339497223137615e-06, + "loss": 3.3341, + "step": 2544640 + }, + { + "epoch": 0.01, + "learning_rate": 8.331111275627097e-06, + "loss": 3.3313, + "step": 2545152 + }, + { + "epoch": 0.01, + "learning_rate": 8.322725328116577e-06, + "loss": 3.324, + "step": 2545664 + }, + { + "epoch": 0.01, + "learning_rate": 8.314355759409786e-06, + "loss": 3.3282, + "step": 2546176 + }, + { + "epoch": 0.01, + "learning_rate": 8.305969811899267e-06, + "loss": 3.3197, + "step": 2546688 + }, + { + "epoch": 0.01, + "learning_rate": 8.297583864388747e-06, + "loss": 3.3453, + "step": 2547200 + }, + { + "epoch": 0.01, + "learning_rate": 8.289197916878226e-06, + "loss": 3.3209, + "step": 2547712 + }, + { + "epoch": 0.01, + "learning_rate": 8.280811969367706e-06, + "loss": 3.3409, + "step": 2548224 + }, + { + "epoch": 0.01, + "learning_rate": 8.272442400660918e-06, + "loss": 3.3318, + "step": 2548736 + }, + { + "epoch": 0.01, + "learning_rate": 8.264056453150398e-06, + "loss": 3.3254, + "step": 2549248 + }, + { + "epoch": 0.01, + "learning_rate": 8.255670505639878e-06, + "loss": 3.3324, + "step": 2549760 + }, + { + "epoch": 0.01, + "learning_rate": 8.247300936933089e-06, + "loss": 3.3321, + "step": 2550272 + }, + { + "epoch": 0.01, + "learning_rate": 8.238914989422569e-06, + "loss": 3.3271, + "step": 2550784 + }, + { + "epoch": 0.01, + "learning_rate": 8.230529041912049e-06, + "loss": 3.3265, + "step": 2551296 + }, + { + "epoch": 0.01, + "learning_rate": 8.222143094401529e-06, + "loss": 3.3409, + "step": 2551808 + }, + { + "epoch": 0.01, + "learning_rate": 8.213757146891009e-06, + "loss": 3.3329, + "step": 2552320 + }, + { + "epoch": 0.01, + "learning_rate": 8.205371199380489e-06, + "loss": 3.3261, + "step": 2552832 + }, + { + "epoch": 0.01, + "learning_rate": 8.1970016306737e-06, + "loss": 3.3269, + "step": 2553344 + }, + { + "epoch": 0.01, + "learning_rate": 8.18861568316318e-06, + "loss": 3.3285, + "step": 2553856 + }, + { + "epoch": 0.01, + "learning_rate": 8.18022973565266e-06, + "loss": 3.3271, + "step": 2554368 + }, + { + "epoch": 0.01, + "learning_rate": 8.17184378814214e-06, + "loss": 3.3434, + "step": 2554880 + }, + { + "epoch": 0.01, + "learning_rate": 8.16347421943535e-06, + "loss": 3.329, + "step": 2555392 + }, + { + "epoch": 0.01, + "learning_rate": 8.155088271924832e-06, + "loss": 3.3434, + "step": 2555904 + }, + { + "epoch": 0.01, + "learning_rate": 8.146702324414312e-06, + "loss": 3.3427, + "step": 2556416 + }, + { + "epoch": 0.01, + "learning_rate": 8.13831637690379e-06, + "loss": 3.3375, + "step": 2556928 + }, + { + "epoch": 0.01, + "learning_rate": 8.12993042939327e-06, + "loss": 3.3304, + "step": 2557440 + }, + { + "epoch": 0.01, + "learning_rate": 8.121560860686482e-06, + "loss": 3.3417, + "step": 2557952 + }, + { + "epoch": 0.01, + "learning_rate": 8.113174913175962e-06, + "loss": 3.3407, + "step": 2558464 + }, + { + "epoch": 0.01, + "learning_rate": 8.10478896566544e-06, + "loss": 3.335, + "step": 2558976 + }, + { + "epoch": 0.01, + "learning_rate": 8.096403018154922e-06, + "loss": 3.3336, + "step": 2559488 + }, + { + "epoch": 0.01, + "learning_rate": 8.088033449448133e-06, + "loss": 3.3416, + "step": 2560000 + }, + { + "epoch": 0.01, + "learning_rate": 8.079647501937613e-06, + "loss": 3.3417, + "step": 2560512 + }, + { + "epoch": 0.01, + "learning_rate": 8.071261554427093e-06, + "loss": 3.3308, + "step": 2561024 + }, + { + "epoch": 0.01, + "learning_rate": 8.062875606916573e-06, + "loss": 3.3233, + "step": 2561536 + }, + { + "epoch": 0.01, + "learning_rate": 8.054506038209785e-06, + "loss": 3.3244, + "step": 2562048 + }, + { + "epoch": 0.01, + "learning_rate": 8.046120090699264e-06, + "loss": 3.3383, + "step": 2562560 + }, + { + "epoch": 0.01, + "learning_rate": 8.037734143188744e-06, + "loss": 3.3369, + "step": 2563072 + }, + { + "epoch": 0.01, + "learning_rate": 8.029348195678223e-06, + "loss": 3.3384, + "step": 2563584 + }, + { + "epoch": 0.01, + "learning_rate": 8.020962248167703e-06, + "loss": 3.3314, + "step": 2564096 + }, + { + "epoch": 0.02, + "learning_rate": 8.012576300657183e-06, + "loss": 3.3269, + "step": 2564608 + }, + { + "epoch": 0.02, + "learning_rate": 8.004206731950394e-06, + "loss": 3.3245, + "step": 2565120 + }, + { + "epoch": 0.02, + "learning_rate": 7.995820784439876e-06, + "loss": 3.331, + "step": 2565632 + }, + { + "epoch": 0.02, + "learning_rate": 7.987434836929354e-06, + "loss": 3.333, + "step": 2566144 + }, + { + "epoch": 0.02, + "learning_rate": 7.979048889418834e-06, + "loss": 3.3364, + "step": 2566656 + }, + { + "epoch": 0.02, + "learning_rate": 7.970662941908314e-06, + "loss": 3.3507, + "step": 2567168 + }, + { + "epoch": 0.02, + "learning_rate": 7.962293373201526e-06, + "loss": 3.3366, + "step": 2567680 + }, + { + "epoch": 0.02, + "learning_rate": 7.953907425691005e-06, + "loss": 3.3256, + "step": 2568192 + }, + { + "epoch": 0.02, + "learning_rate": 7.945521478180486e-06, + "loss": 3.3386, + "step": 2568704 + }, + { + "epoch": 0.02, + "learning_rate": 7.937135530669966e-06, + "loss": 3.3336, + "step": 2569216 + }, + { + "epoch": 0.02, + "learning_rate": 7.928765961963175e-06, + "loss": 3.3384, + "step": 2569728 + }, + { + "epoch": 0.02, + "learning_rate": 7.920380014452657e-06, + "loss": 3.3368, + "step": 2570240 + }, + { + "epoch": 0.02, + "learning_rate": 7.911994066942137e-06, + "loss": 3.3323, + "step": 2570752 + }, + { + "epoch": 0.02, + "learning_rate": 7.903608119431617e-06, + "loss": 3.3309, + "step": 2571264 + }, + { + "epoch": 0.02, + "learning_rate": 7.895222171921097e-06, + "loss": 3.3418, + "step": 2571776 + }, + { + "epoch": 0.02, + "learning_rate": 7.886852603214308e-06, + "loss": 3.3197, + "step": 2572288 + }, + { + "epoch": 0.02, + "learning_rate": 7.878466655703788e-06, + "loss": 3.3301, + "step": 2572800 + }, + { + "epoch": 0.02, + "learning_rate": 7.870080708193268e-06, + "loss": 3.3301, + "step": 2573312 + }, + { + "epoch": 0.02, + "learning_rate": 7.861694760682748e-06, + "loss": 3.3353, + "step": 2573824 + }, + { + "epoch": 0.02, + "learning_rate": 7.853308813172228e-06, + "loss": 3.3233, + "step": 2574336 + }, + { + "epoch": 0.02, + "learning_rate": 7.844922865661708e-06, + "loss": 3.3353, + "step": 2574848 + }, + { + "epoch": 0.02, + "learning_rate": 7.836553296954918e-06, + "loss": 3.325, + "step": 2575360 + }, + { + "epoch": 0.02, + "learning_rate": 7.828167349444398e-06, + "loss": 3.3329, + "step": 2575872 + }, + { + "epoch": 0.02, + "learning_rate": 7.819781401933878e-06, + "loss": 3.3317, + "step": 2576384 + }, + { + "epoch": 0.02, + "learning_rate": 7.811395454423358e-06, + "loss": 3.3312, + "step": 2576896 + }, + { + "epoch": 0.02, + "learning_rate": 7.803009506912838e-06, + "loss": 3.3462, + "step": 2577408 + }, + { + "epoch": 0.02, + "learning_rate": 7.794623559402318e-06, + "loss": 3.3422, + "step": 2577920 + }, + { + "epoch": 0.02, + "learning_rate": 7.786237611891798e-06, + "loss": 3.3333, + "step": 2578432 + }, + { + "epoch": 0.02, + "learning_rate": 7.777851664381278e-06, + "loss": 3.3347, + "step": 2578944 + }, + { + "epoch": 0.02, + "learning_rate": 7.769482095674489e-06, + "loss": 3.3353, + "step": 2579456 + }, + { + "epoch": 0.02, + "learning_rate": 7.76109614816397e-06, + "loss": 3.3296, + "step": 2579968 + }, + { + "epoch": 0.02, + "learning_rate": 7.752710200653449e-06, + "loss": 3.3278, + "step": 2580480 + }, + { + "epoch": 0.02, + "learning_rate": 7.744324253142929e-06, + "loss": 3.3283, + "step": 2580992 + }, + { + "epoch": 0.02, + "learning_rate": 7.735954684436141e-06, + "loss": 3.3297, + "step": 2581504 + }, + { + "epoch": 0.02, + "learning_rate": 7.727568736925621e-06, + "loss": 3.3342, + "step": 2582016 + }, + { + "epoch": 0.02, + "learning_rate": 7.7191827894151e-06, + "loss": 3.3256, + "step": 2582528 + }, + { + "epoch": 0.02, + "learning_rate": 7.71079684190458e-06, + "loss": 3.3334, + "step": 2583040 + }, + { + "epoch": 0.02, + "learning_rate": 7.702410894394061e-06, + "loss": 3.3266, + "step": 2583552 + }, + { + "epoch": 0.02, + "learning_rate": 7.69402494688354e-06, + "loss": 3.3298, + "step": 2584064 + }, + { + "epoch": 0.02, + "learning_rate": 7.685655378176752e-06, + "loss": 3.3281, + "step": 2584576 + }, + { + "epoch": 0.02, + "learning_rate": 7.677269430666232e-06, + "loss": 3.3421, + "step": 2585088 + }, + { + "epoch": 0.02, + "learning_rate": 7.668883483155712e-06, + "loss": 3.3485, + "step": 2585600 + }, + { + "epoch": 0.02, + "learning_rate": 7.66049753564519e-06, + "loss": 3.334, + "step": 2586112 + }, + { + "epoch": 0.02, + "learning_rate": 7.652111588134672e-06, + "loss": 3.3254, + "step": 2586624 + }, + { + "epoch": 0.02, + "learning_rate": 7.643725640624151e-06, + "loss": 3.3326, + "step": 2587136 + }, + { + "epoch": 0.02, + "learning_rate": 7.63533969311363e-06, + "loss": 3.335, + "step": 2587648 + }, + { + "epoch": 0.02, + "learning_rate": 7.626970124406841e-06, + "loss": 3.337, + "step": 2588160 + }, + { + "epoch": 0.02, + "learning_rate": 7.618584176896322e-06, + "loss": 3.3356, + "step": 2588672 + }, + { + "epoch": 0.02, + "learning_rate": 7.610198229385802e-06, + "loss": 3.3386, + "step": 2589184 + }, + { + "epoch": 0.02, + "learning_rate": 7.601812281875281e-06, + "loss": 3.3295, + "step": 2589696 + }, + { + "epoch": 0.02, + "learning_rate": 7.593426334364761e-06, + "loss": 3.3376, + "step": 2590208 + }, + { + "epoch": 0.02, + "learning_rate": 7.585056765657973e-06, + "loss": 3.3312, + "step": 2590720 + }, + { + "epoch": 0.02, + "learning_rate": 7.576670818147452e-06, + "loss": 3.3372, + "step": 2591232 + }, + { + "epoch": 0.02, + "learning_rate": 7.568284870636933e-06, + "loss": 3.3291, + "step": 2591744 + }, + { + "epoch": 0.02, + "learning_rate": 7.559898923126413e-06, + "loss": 3.3241, + "step": 2592256 + }, + { + "epoch": 0.02, + "learning_rate": 7.551529354419624e-06, + "loss": 3.3408, + "step": 2592768 + }, + { + "epoch": 0.02, + "learning_rate": 7.5431434069091035e-06, + "loss": 3.3321, + "step": 2593280 + }, + { + "epoch": 0.02, + "learning_rate": 7.5347574593985834e-06, + "loss": 3.3408, + "step": 2593792 + }, + { + "epoch": 0.02, + "learning_rate": 7.526371511888064e-06, + "loss": 3.3226, + "step": 2594304 + }, + { + "epoch": 0.02, + "learning_rate": 7.517985564377543e-06, + "loss": 3.3289, + "step": 2594816 + }, + { + "epoch": 0.03, + "eval_loss": 3.864877462387085, + "eval_runtime": 312.8313, + "eval_samples_per_second": 1219.798, + "eval_steps_per_second": 38.12, + "step": 2594880 + }, + { + "epoch": 1.0, + "learning_rate": 7.509615995670755e-06, + "loss": 3.3285, + "step": 2595328 + }, + { + "epoch": 1.0, + "learning_rate": 7.501230048160235e-06, + "loss": 3.3265, + "step": 2595840 + }, + { + "epoch": 1.0, + "learning_rate": 7.492844100649715e-06, + "loss": 3.3401, + "step": 2596352 + }, + { + "epoch": 1.0, + "learning_rate": 7.484458153139194e-06, + "loss": 3.3295, + "step": 2596864 + }, + { + "epoch": 1.0, + "learning_rate": 7.476088584432406e-06, + "loss": 3.3459, + "step": 2597376 + }, + { + "epoch": 1.0, + "learning_rate": 7.4677026369218864e-06, + "loss": 3.3291, + "step": 2597888 + }, + { + "epoch": 1.0, + "learning_rate": 7.459316689411366e-06, + "loss": 3.3268, + "step": 2598400 + }, + { + "epoch": 1.0, + "learning_rate": 7.4509307419008455e-06, + "loss": 3.3211, + "step": 2598912 + }, + { + "epoch": 1.0, + "learning_rate": 7.4425447943903255e-06, + "loss": 3.3344, + "step": 2599424 + }, + { + "epoch": 1.0, + "learning_rate": 7.434158846879806e-06, + "loss": 3.3325, + "step": 2599936 + }, + { + "epoch": 1.0, + "learning_rate": 7.425789278173016e-06, + "loss": 3.3369, + "step": 2600448 + }, + { + "epoch": 1.0, + "learning_rate": 7.417403330662496e-06, + "loss": 3.3333, + "step": 2600960 + }, + { + "epoch": 1.0, + "learning_rate": 7.409017383151977e-06, + "loss": 3.3266, + "step": 2601472 + }, + { + "epoch": 1.0, + "learning_rate": 7.400631435641457e-06, + "loss": 3.3219, + "step": 2601984 + }, + { + "epoch": 1.0, + "learning_rate": 7.392245488130936e-06, + "loss": 3.3223, + "step": 2602496 + }, + { + "epoch": 1.0, + "learning_rate": 7.383875919424148e-06, + "loss": 3.3244, + "step": 2603008 + }, + { + "epoch": 1.0, + "learning_rate": 7.3754899719136285e-06, + "loss": 3.3238, + "step": 2603520 + }, + { + "epoch": 1.0, + "learning_rate": 7.367104024403107e-06, + "loss": 3.327, + "step": 2604032 + }, + { + "epoch": 1.0, + "learning_rate": 7.3587180768925875e-06, + "loss": 3.3212, + "step": 2604544 + }, + { + "epoch": 1.0, + "learning_rate": 7.3503321293820675e-06, + "loss": 3.3467, + "step": 2605056 + }, + { + "epoch": 1.0, + "learning_rate": 7.341946181871548e-06, + "loss": 3.3314, + "step": 2605568 + }, + { + "epoch": 1.0, + "learning_rate": 7.333576613164758e-06, + "loss": 3.3365, + "step": 2606080 + }, + { + "epoch": 1.0, + "learning_rate": 7.325190665654238e-06, + "loss": 3.3264, + "step": 2606592 + }, + { + "epoch": 1.0, + "learning_rate": 7.316804718143719e-06, + "loss": 3.3386, + "step": 2607104 + }, + { + "epoch": 1.0, + "learning_rate": 7.308418770633198e-06, + "loss": 3.3201, + "step": 2607616 + }, + { + "epoch": 1.0, + "learning_rate": 7.300032823122678e-06, + "loss": 3.3298, + "step": 2608128 + }, + { + "epoch": 1.0, + "learning_rate": 7.29166325441589e-06, + "loss": 3.3262, + "step": 2608640 + }, + { + "epoch": 1.0, + "learning_rate": 7.28327730690537e-06, + "loss": 3.3262, + "step": 2609152 + }, + { + "epoch": 1.0, + "learning_rate": 7.274891359394849e-06, + "loss": 3.3145, + "step": 2609664 + }, + { + "epoch": 1.01, + "learning_rate": 7.2665054118843296e-06, + "loss": 3.319, + "step": 2610176 + }, + { + "epoch": 1.01, + "learning_rate": 7.258135843177541e-06, + "loss": 3.3309, + "step": 2610688 + }, + { + "epoch": 1.01, + "learning_rate": 7.249749895667021e-06, + "loss": 3.3321, + "step": 2611200 + }, + { + "epoch": 1.01, + "learning_rate": 7.2413639481565e-06, + "loss": 3.335, + "step": 2611712 + }, + { + "epoch": 1.01, + "learning_rate": 7.23297800064598e-06, + "loss": 3.3357, + "step": 2612224 + }, + { + "epoch": 1.01, + "learning_rate": 7.224592053135461e-06, + "loss": 3.3277, + "step": 2612736 + }, + { + "epoch": 1.01, + "learning_rate": 7.216222484428671e-06, + "loss": 3.3334, + "step": 2613248 + }, + { + "epoch": 1.01, + "learning_rate": 7.207836536918152e-06, + "loss": 3.3247, + "step": 2613760 + }, + { + "epoch": 1.01, + "learning_rate": 7.199450589407632e-06, + "loss": 3.3254, + "step": 2614272 + }, + { + "epoch": 1.01, + "learning_rate": 7.191064641897112e-06, + "loss": 3.3138, + "step": 2614784 + }, + { + "epoch": 1.01, + "learning_rate": 7.182678694386591e-06, + "loss": 3.3331, + "step": 2615296 + }, + { + "epoch": 1.01, + "learning_rate": 7.174309125679802e-06, + "loss": 3.3224, + "step": 2615808 + }, + { + "epoch": 1.01, + "learning_rate": 7.165923178169283e-06, + "loss": 3.3349, + "step": 2616320 + }, + { + "epoch": 1.01, + "learning_rate": 7.1575372306587615e-06, + "loss": 3.327, + "step": 2616832 + }, + { + "epoch": 1.01, + "learning_rate": 7.149151283148242e-06, + "loss": 3.3216, + "step": 2617344 + }, + { + "epoch": 1.01, + "learning_rate": 7.140765335637722e-06, + "loss": 3.3377, + "step": 2617856 + }, + { + "epoch": 1.01, + "learning_rate": 7.132395766930934e-06, + "loss": 3.3251, + "step": 2618368 + }, + { + "epoch": 1.01, + "learning_rate": 7.124009819420413e-06, + "loss": 3.3228, + "step": 2618880 + }, + { + "epoch": 1.01, + "learning_rate": 7.115623871909893e-06, + "loss": 3.306, + "step": 2619392 + }, + { + "epoch": 1.01, + "learning_rate": 7.107237924399374e-06, + "loss": 3.3254, + "step": 2619904 + }, + { + "epoch": 1.01, + "learning_rate": 7.098851976888853e-06, + "loss": 3.3292, + "step": 2620416 + }, + { + "epoch": 1.01, + "learning_rate": 7.090466029378333e-06, + "loss": 3.3237, + "step": 2620928 + }, + { + "epoch": 1.01, + "learning_rate": 7.082080081867813e-06, + "loss": 3.3268, + "step": 2621440 + }, + { + "epoch": 1.01, + "learning_rate": 7.073694134357292e-06, + "loss": 3.3123, + "step": 2621952 + }, + { + "epoch": 1.01, + "learning_rate": 7.0653245656505035e-06, + "loss": 3.3222, + "step": 2622464 + }, + { + "epoch": 1.01, + "learning_rate": 7.056938618139984e-06, + "loss": 3.3113, + "step": 2622976 + }, + { + "epoch": 1.01, + "learning_rate": 7.048552670629464e-06, + "loss": 3.336, + "step": 2623488 + }, + { + "epoch": 1.01, + "learning_rate": 7.040166723118943e-06, + "loss": 3.3134, + "step": 2624000 + }, + { + "epoch": 1.01, + "learning_rate": 7.031780775608423e-06, + "loss": 3.3312, + "step": 2624512 + }, + { + "epoch": 1.01, + "learning_rate": 7.023411206901635e-06, + "loss": 3.3275, + "step": 2625024 + }, + { + "epoch": 1.01, + "learning_rate": 7.015025259391116e-06, + "loss": 3.3121, + "step": 2625536 + }, + { + "epoch": 1.01, + "learning_rate": 7.006639311880595e-06, + "loss": 3.3206, + "step": 2626048 + }, + { + "epoch": 1.01, + "learning_rate": 6.998253364370075e-06, + "loss": 3.3265, + "step": 2626560 + }, + { + "epoch": 1.01, + "learning_rate": 6.989867416859555e-06, + "loss": 3.3156, + "step": 2627072 + }, + { + "epoch": 1.01, + "learning_rate": 6.981481469349034e-06, + "loss": 3.3198, + "step": 2627584 + }, + { + "epoch": 1.01, + "learning_rate": 6.973095521838515e-06, + "loss": 3.3294, + "step": 2628096 + }, + { + "epoch": 1.01, + "learning_rate": 6.964709574327995e-06, + "loss": 3.3262, + "step": 2628608 + }, + { + "epoch": 1.01, + "learning_rate": 6.956340005621206e-06, + "loss": 3.3137, + "step": 2629120 + }, + { + "epoch": 1.01, + "learning_rate": 6.947970436914416e-06, + "loss": 3.3196, + "step": 2629632 + }, + { + "epoch": 1.01, + "learning_rate": 6.939584489403897e-06, + "loss": 3.3161, + "step": 2630144 + }, + { + "epoch": 1.01, + "learning_rate": 6.931198541893377e-06, + "loss": 3.3204, + "step": 2630656 + }, + { + "epoch": 1.01, + "learning_rate": 6.922812594382856e-06, + "loss": 3.3345, + "step": 2631168 + }, + { + "epoch": 1.01, + "learning_rate": 6.914426646872337e-06, + "loss": 3.3194, + "step": 2631680 + }, + { + "epoch": 1.01, + "learning_rate": 6.9060570781655485e-06, + "loss": 3.3348, + "step": 2632192 + }, + { + "epoch": 1.01, + "learning_rate": 6.8976711306550285e-06, + "loss": 3.3335, + "step": 2632704 + }, + { + "epoch": 1.01, + "learning_rate": 6.889285183144508e-06, + "loss": 3.3311, + "step": 2633216 + }, + { + "epoch": 1.01, + "learning_rate": 6.8808992356339876e-06, + "loss": 3.3191, + "step": 2633728 + }, + { + "epoch": 1.01, + "learning_rate": 6.872529666927199e-06, + "loss": 3.3336, + "step": 2634240 + }, + { + "epoch": 1.01, + "learning_rate": 6.86414371941668e-06, + "loss": 3.3289, + "step": 2634752 + }, + { + "epoch": 1.01, + "learning_rate": 6.855757771906158e-06, + "loss": 3.3272, + "step": 2635264 + }, + { + "epoch": 1.01, + "learning_rate": 6.847371824395639e-06, + "loss": 3.3235, + "step": 2635776 + }, + { + "epoch": 1.01, + "learning_rate": 6.839002255688851e-06, + "loss": 3.3297, + "step": 2636288 + }, + { + "epoch": 1.01, + "learning_rate": 6.83061630817833e-06, + "loss": 3.337, + "step": 2636800 + }, + { + "epoch": 1.01, + "learning_rate": 6.82223036066781e-06, + "loss": 3.3234, + "step": 2637312 + }, + { + "epoch": 1.01, + "learning_rate": 6.81384441315729e-06, + "loss": 3.3109, + "step": 2637824 + }, + { + "epoch": 1.01, + "learning_rate": 6.805474844450501e-06, + "loss": 3.3151, + "step": 2638336 + }, + { + "epoch": 1.01, + "learning_rate": 6.7970888969399805e-06, + "loss": 3.3303, + "step": 2638848 + }, + { + "epoch": 1.01, + "learning_rate": 6.788702949429461e-06, + "loss": 3.3309, + "step": 2639360 + }, + { + "epoch": 1.01, + "learning_rate": 6.780317001918941e-06, + "loss": 3.3329, + "step": 2639872 + }, + { + "epoch": 1.01, + "learning_rate": 6.77193105440842e-06, + "loss": 3.3209, + "step": 2640384 + }, + { + "epoch": 1.02, + "learning_rate": 6.7635451068979e-06, + "loss": 3.3194, + "step": 2640896 + }, + { + "epoch": 1.02, + "learning_rate": 6.755159159387381e-06, + "loss": 3.3143, + "step": 2641408 + }, + { + "epoch": 1.02, + "learning_rate": 6.746789590680593e-06, + "loss": 3.3196, + "step": 2641920 + }, + { + "epoch": 1.02, + "learning_rate": 6.738403643170072e-06, + "loss": 3.3257, + "step": 2642432 + }, + { + "epoch": 1.02, + "learning_rate": 6.730017695659552e-06, + "loss": 3.3282, + "step": 2642944 + }, + { + "epoch": 1.02, + "learning_rate": 6.721631748149032e-06, + "loss": 3.3425, + "step": 2643456 + }, + { + "epoch": 1.02, + "learning_rate": 6.713262179442243e-06, + "loss": 3.3259, + "step": 2643968 + }, + { + "epoch": 1.02, + "learning_rate": 6.7048762319317225e-06, + "loss": 3.3191, + "step": 2644480 + }, + { + "epoch": 1.02, + "learning_rate": 6.696490284421203e-06, + "loss": 3.3295, + "step": 2644992 + }, + { + "epoch": 1.02, + "learning_rate": 6.688104336910683e-06, + "loss": 3.3219, + "step": 2645504 + }, + { + "epoch": 1.02, + "learning_rate": 6.679734768203893e-06, + "loss": 3.3307, + "step": 2646016 + }, + { + "epoch": 1.02, + "learning_rate": 6.671348820693374e-06, + "loss": 3.3264, + "step": 2646528 + }, + { + "epoch": 1.02, + "learning_rate": 6.662962873182854e-06, + "loss": 3.3242, + "step": 2647040 + }, + { + "epoch": 1.02, + "learning_rate": 6.654576925672335e-06, + "loss": 3.3228, + "step": 2647552 + }, + { + "epoch": 1.02, + "learning_rate": 6.646190978161813e-06, + "loss": 3.3316, + "step": 2648064 + }, + { + "epoch": 1.02, + "learning_rate": 6.637805030651294e-06, + "loss": 3.3112, + "step": 2648576 + }, + { + "epoch": 1.02, + "learning_rate": 6.6294354619445055e-06, + "loss": 3.3239, + "step": 2649088 + }, + { + "epoch": 1.02, + "learning_rate": 6.621049514433985e-06, + "loss": 3.3181, + "step": 2649600 + }, + { + "epoch": 1.02, + "learning_rate": 6.6126635669234645e-06, + "loss": 3.3253, + "step": 2650112 + }, + { + "epoch": 1.02, + "learning_rate": 6.604277619412945e-06, + "loss": 3.3158, + "step": 2650624 + }, + { + "epoch": 1.02, + "learning_rate": 6.595891671902425e-06, + "loss": 3.3259, + "step": 2651136 + }, + { + "epoch": 1.02, + "learning_rate": 6.587522103195635e-06, + "loss": 3.3158, + "step": 2651648 + }, + { + "epoch": 1.02, + "learning_rate": 6.579136155685116e-06, + "loss": 3.3218, + "step": 2652160 + }, + { + "epoch": 1.02, + "learning_rate": 6.570750208174596e-06, + "loss": 3.3247, + "step": 2652672 + }, + { + "epoch": 1.02, + "learning_rate": 6.562364260664075e-06, + "loss": 3.3213, + "step": 2653184 + }, + { + "epoch": 1.02, + "learning_rate": 6.553978313153555e-06, + "loss": 3.3383, + "step": 2653696 + }, + { + "epoch": 1.02, + "learning_rate": 6.545608744446767e-06, + "loss": 3.3341, + "step": 2654208 + }, + { + "epoch": 1.02, + "learning_rate": 6.5372227969362475e-06, + "loss": 3.3275, + "step": 2654720 + }, + { + "epoch": 1.02, + "learning_rate": 6.528836849425727e-06, + "loss": 3.3208, + "step": 2655232 + }, + { + "epoch": 1.02, + "learning_rate": 6.5204509019152066e-06, + "loss": 3.3258, + "step": 2655744 + }, + { + "epoch": 1.02, + "learning_rate": 6.5120649544046865e-06, + "loss": 3.3214, + "step": 2656256 + }, + { + "epoch": 1.02, + "learning_rate": 6.503695385697898e-06, + "loss": 3.3209, + "step": 2656768 + }, + { + "epoch": 1.02, + "learning_rate": 6.495309438187377e-06, + "loss": 3.3223, + "step": 2657280 + }, + { + "epoch": 1.02, + "learning_rate": 6.486923490676858e-06, + "loss": 3.3182, + "step": 2657792 + }, + { + "epoch": 1.02, + "learning_rate": 6.478537543166338e-06, + "loss": 3.3265, + "step": 2658304 + }, + { + "epoch": 1.02, + "learning_rate": 6.470167974459548e-06, + "loss": 3.3142, + "step": 2658816 + }, + { + "epoch": 1.02, + "learning_rate": 6.461782026949029e-06, + "loss": 3.3254, + "step": 2659328 + }, + { + "epoch": 1.02, + "learning_rate": 6.453396079438509e-06, + "loss": 3.3188, + "step": 2659840 + }, + { + "epoch": 1.02, + "learning_rate": 6.445010131927988e-06, + "loss": 3.3212, + "step": 2660352 + }, + { + "epoch": 1.02, + "learning_rate": 6.4366405632211995e-06, + "loss": 3.3152, + "step": 2660864 + }, + { + "epoch": 1.02, + "learning_rate": 6.42825461571068e-06, + "loss": 3.3364, + "step": 2661376 + }, + { + "epoch": 1.02, + "learning_rate": 6.41986866820016e-06, + "loss": 3.3395, + "step": 2661888 + }, + { + "epoch": 1.02, + "learning_rate": 6.411482720689639e-06, + "loss": 3.3271, + "step": 2662400 + }, + { + "epoch": 1.02, + "learning_rate": 6.403096773179119e-06, + "loss": 3.3121, + "step": 2662912 + }, + { + "epoch": 1.02, + "learning_rate": 6.3947108256686e-06, + "loss": 3.3258, + "step": 2663424 + }, + { + "epoch": 1.02, + "learning_rate": 6.386324878158078e-06, + "loss": 3.3231, + "step": 2663936 + }, + { + "epoch": 1.02, + "learning_rate": 6.377938930647559e-06, + "loss": 3.3316, + "step": 2664448 + }, + { + "epoch": 1.02, + "learning_rate": 6.369569361940771e-06, + "loss": 3.3227, + "step": 2664960 + }, + { + "epoch": 1.02, + "learning_rate": 6.361183414430251e-06, + "loss": 3.3275, + "step": 2665472 + }, + { + "epoch": 1.02, + "learning_rate": 6.35279746691973e-06, + "loss": 3.3215, + "step": 2665984 + }, + { + "epoch": 1.02, + "learning_rate": 6.34441151940921e-06, + "loss": 3.3284, + "step": 2666496 + }, + { + "epoch": 1.02, + "learning_rate": 6.3360419507024215e-06, + "loss": 3.3238, + "step": 2667008 + }, + { + "epoch": 1.02, + "learning_rate": 6.327656003191902e-06, + "loss": 3.3259, + "step": 2667520 + }, + { + "epoch": 1.02, + "learning_rate": 6.319270055681381e-06, + "loss": 3.3205, + "step": 2668032 + }, + { + "epoch": 1.02, + "learning_rate": 6.310884108170861e-06, + "loss": 3.3155, + "step": 2668544 + }, + { + "epoch": 1.02, + "learning_rate": 6.302514539464073e-06, + "loss": 3.3306, + "step": 2669056 + }, + { + "epoch": 1.02, + "learning_rate": 6.294128591953552e-06, + "loss": 3.3269, + "step": 2669568 + }, + { + "epoch": 1.02, + "learning_rate": 6.285742644443032e-06, + "loss": 3.3255, + "step": 2670080 + }, + { + "epoch": 1.02, + "learning_rate": 6.277356696932513e-06, + "loss": 3.3142, + "step": 2670592 + }, + { + "epoch": 1.02, + "learning_rate": 6.268970749421993e-06, + "loss": 3.3182, + "step": 2671104 + }, + { + "epoch": 1.03, + "eval_loss": 3.8660049438476562, + "eval_runtime": 312.4531, + "eval_samples_per_second": 1221.274, + "eval_steps_per_second": 38.166, + "step": 2671200 + }, + { + "epoch": 0.0, + "learning_rate": 6.2606011807152036e-06, + "loss": 3.3167, + "step": 2671616 + }, + { + "epoch": 0.0, + "learning_rate": 6.2522152332046835e-06, + "loss": 3.3217, + "step": 2672128 + }, + { + "epoch": 0.0, + "learning_rate": 6.2438292856941635e-06, + "loss": 3.3286, + "step": 2672640 + }, + { + "epoch": 0.0, + "learning_rate": 6.2354433381836434e-06, + "loss": 3.3209, + "step": 2673152 + }, + { + "epoch": 0.0, + "learning_rate": 6.227073769476855e-06, + "loss": 3.3366, + "step": 2673664 + }, + { + "epoch": 0.0, + "learning_rate": 6.218687821966335e-06, + "loss": 3.3214, + "step": 2674176 + }, + { + "epoch": 0.0, + "learning_rate": 6.210301874455814e-06, + "loss": 3.3201, + "step": 2674688 + }, + { + "epoch": 0.0, + "learning_rate": 6.201915926945295e-06, + "loss": 3.3104, + "step": 2675200 + }, + { + "epoch": 0.0, + "learning_rate": 6.193529979434774e-06, + "loss": 3.327, + "step": 2675712 + }, + { + "epoch": 0.0, + "learning_rate": 6.185144031924255e-06, + "loss": 3.3241, + "step": 2676224 + }, + { + "epoch": 0.0, + "learning_rate": 6.176774463217466e-06, + "loss": 3.3273, + "step": 2676736 + }, + { + "epoch": 0.0, + "learning_rate": 6.168388515706946e-06, + "loss": 3.3253, + "step": 2677248 + }, + { + "epoch": 0.0, + "learning_rate": 6.1600025681964256e-06, + "loss": 3.3179, + "step": 2677760 + }, + { + "epoch": 0.0, + "learning_rate": 6.151616620685905e-06, + "loss": 3.3149, + "step": 2678272 + }, + { + "epoch": 0.0, + "learning_rate": 6.143247051979117e-06, + "loss": 3.3132, + "step": 2678784 + }, + { + "epoch": 0.0, + "learning_rate": 6.134861104468596e-06, + "loss": 3.3187, + "step": 2679296 + }, + { + "epoch": 0.0, + "learning_rate": 6.126475156958077e-06, + "loss": 3.3152, + "step": 2679808 + }, + { + "epoch": 0.0, + "learning_rate": 6.118089209447556e-06, + "loss": 3.3162, + "step": 2680320 + }, + { + "epoch": 0.0, + "learning_rate": 6.109703261937036e-06, + "loss": 3.3116, + "step": 2680832 + }, + { + "epoch": 0.0, + "learning_rate": 6.101317314426516e-06, + "loss": 3.3408, + "step": 2681344 + }, + { + "epoch": 0.0, + "learning_rate": 6.092931366915996e-06, + "loss": 3.3235, + "step": 2681856 + }, + { + "epoch": 0.0, + "learning_rate": 6.084561798209208e-06, + "loss": 3.321, + "step": 2682368 + }, + { + "epoch": 0.0, + "learning_rate": 6.076175850698687e-06, + "loss": 3.3218, + "step": 2682880 + }, + { + "epoch": 0.0, + "learning_rate": 6.067789903188168e-06, + "loss": 3.3262, + "step": 2683392 + }, + { + "epoch": 0.0, + "learning_rate": 6.059403955677647e-06, + "loss": 3.3146, + "step": 2683904 + }, + { + "epoch": 0.0, + "learning_rate": 6.051034386970858e-06, + "loss": 3.3258, + "step": 2684416 + }, + { + "epoch": 0.0, + "learning_rate": 6.042648439460338e-06, + "loss": 3.3178, + "step": 2684928 + }, + { + "epoch": 0.0, + "learning_rate": 6.034262491949818e-06, + "loss": 3.3159, + "step": 2685440 + }, + { + "epoch": 0.0, + "learning_rate": 6.025876544439298e-06, + "loss": 3.3032, + "step": 2685952 + }, + { + "epoch": 0.01, + "learning_rate": 6.017490596928778e-06, + "loss": 3.3135, + "step": 2686464 + }, + { + "epoch": 0.01, + "learning_rate": 6.00912102822199e-06, + "loss": 3.3188, + "step": 2686976 + }, + { + "epoch": 0.01, + "learning_rate": 6.000735080711469e-06, + "loss": 3.3216, + "step": 2687488 + }, + { + "epoch": 0.01, + "learning_rate": 5.99234913320095e-06, + "loss": 3.3298, + "step": 2688000 + }, + { + "epoch": 0.01, + "learning_rate": 5.983963185690429e-06, + "loss": 3.3257, + "step": 2688512 + }, + { + "epoch": 0.01, + "learning_rate": 5.975577238179909e-06, + "loss": 3.3148, + "step": 2689024 + }, + { + "epoch": 0.01, + "learning_rate": 5.967191290669389e-06, + "loss": 3.3284, + "step": 2689536 + }, + { + "epoch": 0.01, + "learning_rate": 5.9588217219626e-06, + "loss": 3.3141, + "step": 2690048 + }, + { + "epoch": 0.01, + "learning_rate": 5.95043577445208e-06, + "loss": 3.32, + "step": 2690560 + }, + { + "epoch": 0.01, + "learning_rate": 5.94204982694156e-06, + "loss": 3.3042, + "step": 2691072 + }, + { + "epoch": 0.01, + "learning_rate": 5.93366387943104e-06, + "loss": 3.321, + "step": 2691584 + }, + { + "epoch": 0.01, + "learning_rate": 5.925294310724251e-06, + "loss": 3.3142, + "step": 2692096 + }, + { + "epoch": 0.01, + "learning_rate": 5.916908363213732e-06, + "loss": 3.3253, + "step": 2692608 + }, + { + "epoch": 0.01, + "learning_rate": 5.908522415703211e-06, + "loss": 3.3198, + "step": 2693120 + }, + { + "epoch": 0.01, + "learning_rate": 5.900136468192691e-06, + "loss": 3.3122, + "step": 2693632 + }, + { + "epoch": 0.01, + "learning_rate": 5.891750520682171e-06, + "loss": 3.3283, + "step": 2694144 + }, + { + "epoch": 0.01, + "learning_rate": 5.883380951975382e-06, + "loss": 3.3183, + "step": 2694656 + }, + { + "epoch": 0.01, + "learning_rate": 5.8749950044648624e-06, + "loss": 3.3107, + "step": 2695168 + }, + { + "epoch": 0.01, + "learning_rate": 5.8666090569543415e-06, + "loss": 3.2996, + "step": 2695680 + }, + { + "epoch": 0.01, + "learning_rate": 5.858223109443822e-06, + "loss": 3.3127, + "step": 2696192 + }, + { + "epoch": 0.01, + "learning_rate": 5.8498371619333015e-06, + "loss": 3.3197, + "step": 2696704 + }, + { + "epoch": 0.01, + "learning_rate": 5.841467593226514e-06, + "loss": 3.3154, + "step": 2697216 + }, + { + "epoch": 0.01, + "learning_rate": 5.833081645715993e-06, + "loss": 3.3168, + "step": 2697728 + }, + { + "epoch": 0.01, + "learning_rate": 5.824695698205473e-06, + "loss": 3.3049, + "step": 2698240 + }, + { + "epoch": 0.01, + "learning_rate": 5.816309750694953e-06, + "loss": 3.3144, + "step": 2698752 + }, + { + "epoch": 0.01, + "learning_rate": 5.807923803184433e-06, + "loss": 3.3028, + "step": 2699264 + }, + { + "epoch": 0.01, + "learning_rate": 5.7995542344776446e-06, + "loss": 3.324, + "step": 2699776 + }, + { + "epoch": 0.01, + "learning_rate": 5.791168286967124e-06, + "loss": 3.3116, + "step": 2700288 + }, + { + "epoch": 0.01, + "learning_rate": 5.7827823394566045e-06, + "loss": 3.3192, + "step": 2700800 + }, + { + "epoch": 0.01, + "learning_rate": 5.7743963919460836e-06, + "loss": 3.3187, + "step": 2701312 + }, + { + "epoch": 0.01, + "learning_rate": 5.766026823239295e-06, + "loss": 3.3083, + "step": 2701824 + }, + { + "epoch": 0.01, + "learning_rate": 5.757640875728775e-06, + "loss": 3.3079, + "step": 2702336 + }, + { + "epoch": 0.01, + "learning_rate": 5.749254928218255e-06, + "loss": 3.3189, + "step": 2702848 + }, + { + "epoch": 0.01, + "learning_rate": 5.740868980707735e-06, + "loss": 3.3066, + "step": 2703360 + }, + { + "epoch": 0.01, + "learning_rate": 5.732483033197215e-06, + "loss": 3.3144, + "step": 2703872 + }, + { + "epoch": 0.01, + "learning_rate": 5.724113464490427e-06, + "loss": 3.3162, + "step": 2704384 + }, + { + "epoch": 0.01, + "learning_rate": 5.715727516979906e-06, + "loss": 3.3193, + "step": 2704896 + }, + { + "epoch": 0.01, + "learning_rate": 5.707341569469387e-06, + "loss": 3.3045, + "step": 2705408 + }, + { + "epoch": 0.01, + "learning_rate": 5.698955621958866e-06, + "loss": 3.3122, + "step": 2705920 + }, + { + "epoch": 0.01, + "learning_rate": 5.690569674448346e-06, + "loss": 3.3054, + "step": 2706432 + }, + { + "epoch": 0.01, + "learning_rate": 5.682200105741557e-06, + "loss": 3.31, + "step": 2706944 + }, + { + "epoch": 0.01, + "learning_rate": 5.673814158231037e-06, + "loss": 3.322, + "step": 2707456 + }, + { + "epoch": 0.01, + "learning_rate": 5.665428210720517e-06, + "loss": 3.3115, + "step": 2707968 + }, + { + "epoch": 0.01, + "learning_rate": 5.657042263209997e-06, + "loss": 3.3277, + "step": 2708480 + }, + { + "epoch": 0.01, + "learning_rate": 5.648656315699477e-06, + "loss": 3.3232, + "step": 2708992 + }, + { + "epoch": 0.01, + "learning_rate": 5.640270368188957e-06, + "loss": 3.3238, + "step": 2709504 + }, + { + "epoch": 0.01, + "learning_rate": 5.631884420678436e-06, + "loss": 3.306, + "step": 2710016 + }, + { + "epoch": 0.01, + "learning_rate": 5.623498473167917e-06, + "loss": 3.321, + "step": 2710528 + }, + { + "epoch": 0.01, + "learning_rate": 5.615128904461128e-06, + "loss": 3.3256, + "step": 2711040 + }, + { + "epoch": 0.01, + "learning_rate": 5.606742956950608e-06, + "loss": 3.3117, + "step": 2711552 + }, + { + "epoch": 0.01, + "learning_rate": 5.598357009440088e-06, + "loss": 3.3178, + "step": 2712064 + }, + { + "epoch": 0.01, + "learning_rate": 5.589987440733299e-06, + "loss": 3.3214, + "step": 2712576 + }, + { + "epoch": 0.01, + "learning_rate": 5.581601493222778e-06, + "loss": 3.3297, + "step": 2713088 + }, + { + "epoch": 0.01, + "learning_rate": 5.573215545712259e-06, + "loss": 3.3149, + "step": 2713600 + }, + { + "epoch": 0.01, + "learning_rate": 5.564829598201738e-06, + "loss": 3.3014, + "step": 2714112 + }, + { + "epoch": 0.01, + "learning_rate": 5.55646002949495e-06, + "loss": 3.3076, + "step": 2714624 + }, + { + "epoch": 0.01, + "learning_rate": 5.54807408198443e-06, + "loss": 3.3169, + "step": 2715136 + }, + { + "epoch": 0.01, + "learning_rate": 5.53968813447391e-06, + "loss": 3.3208, + "step": 2715648 + }, + { + "epoch": 0.01, + "learning_rate": 5.53130218696339e-06, + "loss": 3.3203, + "step": 2716160 + }, + { + "epoch": 0.01, + "learning_rate": 5.52291623945287e-06, + "loss": 3.3129, + "step": 2716672 + }, + { + "epoch": 0.02, + "learning_rate": 5.5145466707460814e-06, + "loss": 3.3135, + "step": 2717184 + }, + { + "epoch": 0.02, + "learning_rate": 5.5061607232355605e-06, + "loss": 3.304, + "step": 2717696 + }, + { + "epoch": 0.02, + "learning_rate": 5.4977747757250405e-06, + "loss": 3.3121, + "step": 2718208 + }, + { + "epoch": 0.02, + "learning_rate": 5.4893888282145205e-06, + "loss": 3.3123, + "step": 2718720 + }, + { + "epoch": 0.02, + "learning_rate": 5.481019259507732e-06, + "loss": 3.3266, + "step": 2719232 + }, + { + "epoch": 0.02, + "learning_rate": 5.472633311997212e-06, + "loss": 3.3354, + "step": 2719744 + }, + { + "epoch": 0.02, + "learning_rate": 5.464247364486692e-06, + "loss": 3.3138, + "step": 2720256 + }, + { + "epoch": 0.02, + "learning_rate": 5.455861416976172e-06, + "loss": 3.3087, + "step": 2720768 + }, + { + "epoch": 0.02, + "learning_rate": 5.447475469465652e-06, + "loss": 3.3214, + "step": 2721280 + }, + { + "epoch": 0.02, + "learning_rate": 5.4391059007588635e-06, + "loss": 3.3118, + "step": 2721792 + }, + { + "epoch": 0.02, + "learning_rate": 5.430719953248343e-06, + "loss": 3.3245, + "step": 2722304 + }, + { + "epoch": 0.02, + "learning_rate": 5.422334005737823e-06, + "loss": 3.3144, + "step": 2722816 + }, + { + "epoch": 0.02, + "learning_rate": 5.4139480582273026e-06, + "loss": 3.3162, + "step": 2723328 + }, + { + "epoch": 0.02, + "learning_rate": 5.4055621107167825e-06, + "loss": 3.3151, + "step": 2723840 + }, + { + "epoch": 0.02, + "learning_rate": 5.3971761632062625e-06, + "loss": 3.3242, + "step": 2724352 + }, + { + "epoch": 0.02, + "learning_rate": 5.3887902156957424e-06, + "loss": 3.3038, + "step": 2724864 + }, + { + "epoch": 0.02, + "learning_rate": 5.380420646988954e-06, + "loss": 3.3132, + "step": 2725376 + }, + { + "epoch": 0.02, + "learning_rate": 5.372034699478433e-06, + "loss": 3.3068, + "step": 2725888 + }, + { + "epoch": 0.02, + "learning_rate": 5.363648751967913e-06, + "loss": 3.3204, + "step": 2726400 + }, + { + "epoch": 0.02, + "learning_rate": 5.355262804457394e-06, + "loss": 3.3075, + "step": 2726912 + }, + { + "epoch": 0.02, + "learning_rate": 5.346876856946873e-06, + "loss": 3.3161, + "step": 2727424 + }, + { + "epoch": 0.02, + "learning_rate": 5.338490909436354e-06, + "loss": 3.3093, + "step": 2727936 + }, + { + "epoch": 0.02, + "learning_rate": 5.330121340729565e-06, + "loss": 3.3129, + "step": 2728448 + }, + { + "epoch": 0.02, + "learning_rate": 5.321735393219045e-06, + "loss": 3.3135, + "step": 2728960 + }, + { + "epoch": 0.02, + "learning_rate": 5.3133494457085246e-06, + "loss": 3.3146, + "step": 2729472 + }, + { + "epoch": 0.02, + "learning_rate": 5.304963498198004e-06, + "loss": 3.3266, + "step": 2729984 + }, + { + "epoch": 0.02, + "learning_rate": 5.2965775506874845e-06, + "loss": 3.3286, + "step": 2730496 + }, + { + "epoch": 0.02, + "learning_rate": 5.288207981980695e-06, + "loss": 3.3158, + "step": 2731008 + }, + { + "epoch": 0.02, + "learning_rate": 5.279822034470175e-06, + "loss": 3.3126, + "step": 2731520 + }, + { + "epoch": 0.02, + "learning_rate": 5.271436086959655e-06, + "loss": 3.315, + "step": 2732032 + }, + { + "epoch": 0.02, + "learning_rate": 5.263050139449135e-06, + "loss": 3.315, + "step": 2732544 + }, + { + "epoch": 0.02, + "learning_rate": 5.254664191938615e-06, + "loss": 3.3085, + "step": 2733056 + }, + { + "epoch": 0.02, + "learning_rate": 5.246294623231827e-06, + "loss": 3.3135, + "step": 2733568 + }, + { + "epoch": 0.02, + "learning_rate": 5.237908675721307e-06, + "loss": 3.3163, + "step": 2734080 + }, + { + "epoch": 0.02, + "learning_rate": 5.229522728210786e-06, + "loss": 3.3141, + "step": 2734592 + }, + { + "epoch": 0.02, + "learning_rate": 5.221136780700267e-06, + "loss": 3.3097, + "step": 2735104 + }, + { + "epoch": 0.02, + "learning_rate": 5.212767211993477e-06, + "loss": 3.3135, + "step": 2735616 + }, + { + "epoch": 0.02, + "learning_rate": 5.204381264482957e-06, + "loss": 3.3096, + "step": 2736128 + }, + { + "epoch": 0.02, + "learning_rate": 5.195995316972437e-06, + "loss": 3.3137, + "step": 2736640 + }, + { + "epoch": 0.02, + "learning_rate": 5.187609369461917e-06, + "loss": 3.306, + "step": 2737152 + }, + { + "epoch": 0.02, + "learning_rate": 5.179239800755129e-06, + "loss": 3.3283, + "step": 2737664 + }, + { + "epoch": 0.02, + "learning_rate": 5.170853853244609e-06, + "loss": 3.3254, + "step": 2738176 + }, + { + "epoch": 0.02, + "learning_rate": 5.162467905734089e-06, + "loss": 3.3229, + "step": 2738688 + }, + { + "epoch": 0.02, + "learning_rate": 5.154081958223568e-06, + "loss": 3.3033, + "step": 2739200 + }, + { + "epoch": 0.02, + "learning_rate": 5.145696010713049e-06, + "loss": 3.3163, + "step": 2739712 + }, + { + "epoch": 0.02, + "learning_rate": 5.1373264420062595e-06, + "loss": 3.32, + "step": 2740224 + }, + { + "epoch": 0.02, + "learning_rate": 5.1289404944957394e-06, + "loss": 3.3182, + "step": 2740736 + }, + { + "epoch": 0.02, + "learning_rate": 5.120554546985219e-06, + "loss": 3.3153, + "step": 2741248 + }, + { + "epoch": 0.02, + "learning_rate": 5.112168599474699e-06, + "loss": 3.3155, + "step": 2741760 + }, + { + "epoch": 0.02, + "learning_rate": 5.103782651964179e-06, + "loss": 3.3153, + "step": 2742272 + }, + { + "epoch": 0.02, + "learning_rate": 5.095396704453658e-06, + "loss": 3.3191, + "step": 2742784 + }, + { + "epoch": 0.02, + "learning_rate": 5.08702713574687e-06, + "loss": 3.314, + "step": 2743296 + }, + { + "epoch": 0.02, + "learning_rate": 5.07864118823635e-06, + "loss": 3.3168, + "step": 2743808 + }, + { + "epoch": 0.02, + "learning_rate": 5.07025524072583e-06, + "loss": 3.313, + "step": 2744320 + }, + { + "epoch": 0.02, + "learning_rate": 5.06186929321531e-06, + "loss": 3.3067, + "step": 2744832 + }, + { + "epoch": 0.02, + "learning_rate": 5.0534997245085216e-06, + "loss": 3.3199, + "step": 2745344 + }, + { + "epoch": 0.02, + "learning_rate": 5.0451137769980015e-06, + "loss": 3.3209, + "step": 2745856 + }, + { + "epoch": 0.02, + "learning_rate": 5.0367278294874815e-06, + "loss": 3.3159, + "step": 2746368 + }, + { + "epoch": 0.02, + "learning_rate": 5.0283418819769614e-06, + "loss": 3.3041, + "step": 2746880 + }, + { + "epoch": 0.02, + "learning_rate": 5.0199559344664405e-06, + "loss": 3.3091, + "step": 2747392 + }, + { + "epoch": 0.03, + "eval_loss": 3.866748332977295, + "eval_runtime": 304.4611, + "eval_samples_per_second": 1253.333, + "eval_steps_per_second": 39.168, + "step": 2747520 + } + ], + "logging_steps": 512, + "max_steps": 3052726, + "num_train_epochs": 9223372036854775807, + "save_steps": 10, + "total_flos": 1.9159299661036954e+18, + "trial_name": null, + "trial_params": null +}